呆博士的疯狂实验室

【论文阅读笔记】NeurIPS2020文章列表Part1

 
  A graph similarity for deep learning
An Unsupervised Information-Theoretic Perceptual Quality Metric
Self-Supervised MultiModal Versatile Networks
Benchmarking Deep Inverse Models over time, and the Neural-Adjoint method
Off-Policy Evaluation and Learning for External Validity under a Covariate Shift
Neural Methods for Point-wise Dependency Estimation
Fast and Flexible Temporal Point Processes with Triangular Maps
Backpropagating Linearly Improves Transferability of Adversarial Examples
PyGlove: Symbolic Programming for Automated Machine Learning
Fourier Sparse Leverage Scores and Approximate Kernel Learning
Improved Algorithms for Online Submodular Maximization via First-order Regret Bounds
Synbols: Probing Learning Algorithms with Synthetic Datasets
Adversarially Robust Streaming Algorithms via Differential Privacy
Trading Personalization for Accuracy: Data Debugging in Collaborative Filtering
Cascaded Text Generation with Markov Transformers
Improving Local Identifiability in Probabilistic Box Embeddings
Permute-and-Flip: A new mechanism for differentially private selection
Deep reconstruction of strange attractors from time series
Reciprocal Adversarial Learning via Characteristic Functions
Statistical Guarantees of Distributed Nearest Neighbor Classification
Stein Self-Repulsive Dynamics: Benefits From Past Samples
The Statistical Complexity of Early-Stopped Mirror Descent
Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
Quantitative Propagation of Chaos for SGD in Wide Neural Networks
A Causal View on Robustness of Neural Networks
Minimax Classification with 0-1 Loss and Performance Guarantees
How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization
Coresets for Regressions with Panel Data
Learning Composable Energy Surrogates for PDE Order Reduction
Efficient Contextual Bandits with Continuous Actions
Achieving Equalized Odds by Resampling Sensitive Attributes
Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates
Hard Shape-Constrained Kernel Machines
A Closer Look at the Training Strategy for Modern Meta-Learning
On the Value of Out-of-Distribution Testing: An Example of Goodhart’s Law
Generalised Bayesian Filtering via Sequential Monte Carlo
Deterministic Approximation for Submodular Maximization over a Matroid in Nearly Linear Time
Flows for simultaneous manifold learning and density estimation
Simultaneous Preference and Metric Learning from Paired Comparisons
Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee
Learning Manifold Implicitly via Explicit Heat-Kernel Learning
Deep Relational Topic Modeling via Graph Poisson Gamma Belief Network
One-bit Supervision for Image Classification
What is being transferred in transfer learning? 
Submodular Maximization Through Barrier Functions
Neural Networks with Recurrent Generative Feedback
Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
Exploiting weakly supervised visual patterns to learn from partial annotations
Improving Inference for Neural Image Compression
Neuron Merging: Compensating for Pruned Neurons
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing
Towards Playing Full MOBA Games with Deep Reinforcement Learning
Rankmax: An Adaptive Projection Alternative to the Softmax Function
Online Agnostic Boosting via Regret Minimization
Causal Intervention for Weakly-Supervised Semantic Segmentation
Belief Propagation Neural Networks
Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality
Post-training Iterative Hierarchical Data Augmentation for Deep Networks
Debugging Tests for Model Explanations
 Robust compressed sensing using generative models 
Fairness without Demographics through Adversarially Reweighted Learning
Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model
Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian
The route to chaos in routing games: When is price of anarchy too optimistic?
Online Algorithm for Unsupervised Sequential Selection with Contextual Information
Adapting Neural Architectures Between Domains
What went wrong and when? Instance-wise feature importance for time-series black-box models
Towards Better Generalization of Adaptive Gradient Methods
Learning Guidance Rewards with Trajectory-space Smoothing
Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization
Tree! I am no Tree! I am a low dimensional Hyperbolic Embedding
Deep Structural Causal Models for Tractable Counterfactual Inference
Convolutional Generation of Textured 3D Meshes
A Statistical Framework for Low-bitwidth Training of Deep Neural Networks
Better Set Representations For Relational Reasoning
AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning
A Combinatorial Perspective on Transfer Learning 
Hardness of Learning Neural Networks with Natural Weights
Higher-Order Spectral Clustering of Directed Graphs
Primal-Dual Mesh Convolutional Neural Networks
The Advantage of Conditional Meta-Learning for Biased Regularization and Fine Tuning
Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
Sinkhorn Barycenter via Functional Gradient Descent
Coresets for Near-Convex Functions
Bayesian Deep Ensembles via the Neural Tangent Kernel
Improved Schemes for Episodic Memory-based Lifelong Learning
Adaptive Sampling for Stochastic Risk-Averse Learning
Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring
Discovering Reinforcement Learning Algorithms
Taming Discrete Integration via the Boon of Dimensionality
Blind Video Temporal Consistency via Deep Video Prior
Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering
Model Selection for Production System via Automated Online Experiments
On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
Adaptation Properties Allow Identification of Optimized Neural Codes
Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems
Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity
Conservative Q-Learning for Offline Reinforcement Learning
Online Influence Maximization under Linear Threshold Model
Ensembling geophysical models with Bayesian Neural Networks
Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation
Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability
Understanding Deep Architecture with Reasoning Layer
Planning in Markov Decision Processes with Gap-Dependent Sample Complexity
Provably Good Batch Off-Policy Reinforcement Learning Without Great Exploration
Detection as Regression: Certified Object Detection with Median Smoothing
Contextual Reserve Price Optimization in Auctions via Mixed Integer Programming
ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks
FleXOR: Trainable Fractional Quantization
The Implications of Local Correlation on Learning Some Deep Functions
Learning to search efficiently for causally near-optimal treatments
A Game Theoretic Analysis of Additive Adversarial Attacks and Defenses
Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
Recurrent Quantum Neural Networks
No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix
A Unifying View of Optimism in Episodic Reinforcement Learning
Continuous Submodular Maximization: Beyond DR-Submodularity
An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits
Assessing SATNet’s Ability to Solve the Symbol Grounding Problem
A Bayesian Nonparametrics View into Deep Representations
On the Similarity between the Laplace and Neural Tangent Kernels
A causal view of compositional zero-shot recognition
HiPPO: Recurrent Memory with Optimal Polynomial Projections
Auto Learning Attention
CASTLE: Regularization via Auxiliary Causal Graph Discovery
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
Explainable Voting
Deep Archimedean Copulas
Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization
UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging
Thunder: a Fast Coordinate Selection Solver for Sparse Learning
Neural Networks Fail to Learn Periodic Functions and How to Fix It
Distribution Matching for Crowd Counting
Correspondence learning via linearly-invariant embedding
Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning
 On Adaptive Attacks to Adversarial Example Defenses
Sinkhorn Natural Gradient for Generative Models
Online Sinkhorn: Optimal Transport distances from sample streams
Ultrahyperbolic Representation Learning
Locally-Adaptive Nonparametric Online Learning
Compositional Generalization via Neural-Symbolic Stack Machines
Graphon Neural Networks and the Transferability of Graph Neural Networks
Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms
Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction
Deep Transformers with Latent Depth
Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows
Statistical control for spatio-temporal MEG/EEG source imaging with desparsified mutli-task Lasso
A Scalable MIP-based Method for Learning Optimal Multivariate Decision Trees
Efficient Exact Verification of Binarized Neural Networks
Ultra-Low Precision 4-bit Training of Deep Neural Networks
Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS
On Numerosity of Deep Neural Networks
Outlier Robust Mean Estimation with Subgaussian Rates via Stability
Self-Supervised Relationship Probing
Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback
Prophet Attention: Predicting Attention with Future Attention
Language Models are Few-Shot Learners
Margins are Insufficient for Explaining Gradient Boosting
Fourier-transform-based attribution priors improve the interpretability and stability of deep learning models for genomics
MomentumRNN: Integrating Momentum into Recurrent Neural Networks
Marginal Utility for Planning in Continuous or Large Discrete Action Spaces
Projected Stein Variational Gradient Descent
Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks
SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
On the equivalence of molecular graph convolution and molecular wave function with poor basis set
The Power of Predictions in Online Control
Learning Affordance Landscapes for Interaction Exploration in 3D Environments
Cooperative Multi-player Bandit Optimization 
Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits
Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout
A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model
Dynamic Fusion of Eye Movement Data and Verbal Narrations in Knowledge-rich Domains
Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward
Optimizing Neural Networks via Koopman Operator Theory
SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence
Adversarial Robustness of Supervised Sparse Coding
Differentiable Meta-Learning of Bandit Policies
Biologically Inspired Mechanisms for Adversarial Robustness
Statistical-Query Lower Bounds via Functional Gradients
Near-Optimal Reinforcement Learning with Self-Play
Network Diffusions via Neural Mean-Field Dynamics
Self-Distillation as Instance-Specific Label Smoothing
Towards Problem-dependent Optimal Learning Rates
Cross-lingual Retrieval for Iterative Self-Supervised Training
Rethinking pooling in graph neural networks
Pointer Graph Networks
Gradient Regularized V-Learning for Dynamic Treatment Regimes
Faster Wasserstein Distance Estimation with the Sinkhorn Divergence
Forethought and Hindsight in Credit Assignment
Robust Recursive Partitioning for Heterogeneous Treatment Effects with Uncertainty Quantification
Rescuing neural spike train models from bad MLE
Lower Bounds and Optimal Algorithms for Personalized Federated Learning
Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework
Deep Imitation Learning for Bimanual Robotic Manipulation
Stationary Activations for Uncertainty Calibration in Deep Learning
Ensemble Distillation for Robust Model Fusion in Federated Learning
Falcon: Fast Spectral Inference on Encrypted Data
On Power Laws in Deep Ensembles
Practical Quasi-Newton Methods for Training Deep Neural Networks
Approximation Based Variance Reduction for Reparameterization Gradients
Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation
Consistent feature selection for analytic deep neural networks
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
Information Maximization for Few-Shot Learning
Inverse Reinforcement Learning from a Gradient-based Learner
Bayesian Multi-type Mean Field Multi-agent Imitation Learning
Bayesian Robust Optimization for Imitation Learning
Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance
Riemannian Continuous Normalizing Flows
Attention-Gated Brain Propagation: How the brain can implement reward-based error backpropagation
Asymptotic Guarantees for Generative Modeling Based on the Smooth Wasserstein Distance
Online Robust Regression via SGD on the l1 loss
PRANK: motion Prediction based on RANKing
Fighting Copycat Agents in Behavioral Cloning from Observation Histories
Tight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model
Structured Prediction for Conditional Meta-Learning
Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient
The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
Stochasticity of Deterministic Gradient Descent: Large Learning Rate for Multiscale Objective Function
Identifying Learning Rules From Neural Network Observables
Optimal Approximation - Smoothness Tradeoffs for Soft-Max Functions
Weakly-Supervised Reinforcement Learning for Controllable Behavior
Improving Policy-Constrained Kidney Exchange via Pre-Screening
Learning abstract structure for drawing by efficient motor program induction
Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? — A Neural Tangent Kernel Perspective
Dual Instrumental Variable Regression
Stochastic Gradient Descent in Correlated Settings: A Study on Gaussian Processes
Interventional Few-Shot Learning
Minimax Value Interval for Off-Policy Evaluation and Policy Optimization
Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning
ShiftAddNet: A Hardware-Inspired Deep Network
Network-to-Network Translation with Conditional Invertible Neural Networks
Intra-Processing Methods for Debiasing Neural Networks
Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems
Model-based Policy Optimization with Unsupervised Model Adaptation
Implicit Regularization and Convergence for Weight Normalization
Geometric All-way Boolean Tensor Decomposition
Modular Meta-Learning with Shrinkage
A/B Testing in Dense Large-Scale Networks: Design and Inference
What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation
Partially View-aligned Clustering
Partial Optimal Tranport with applications on Positive-Unlabeled Learning
Toward the Fundamental Limits of Imitation Learning
Logarithmic Pruning is All You Need
Hold me tight! Influence of discriminative features on deep network boundaries
Learning from Mixtures of Private and Public Populations
Adversarial Weight Perturbation Helps Robust Generalization
Stateful Posted Pricing with Vanishing Regret via Dynamic Deterministic Markov Decision Processes
Adversarial Self-Supervised Contrastive Learning
Normalizing Kalman Filters for Multivariate Time Series Analysis
Learning to summarize with human feedback
Fourier Spectrum Discrepancies in Deep Network Generated Images
Lamina-specific neuronal properties promote robust, stable signal propagation in feedforward networks
Learning Dynamic Belief Graphs to Generalize on Text-Based Games
Triple descent and the two kinds of overfitting: where & why do they appear?
Multimodal Graph Networks for Compositional Generalization in Visual Question Answering
Learning Graph Structure With A Finite-State Automaton Layer
A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions
Unsupervised object-centric video generation and decomposition in 3D
Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization
Multi-label classification: do Hamming loss and subset accuracy really conflict with each other?
A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances
Causal analysis of Covid-19 Spread in Germany
Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms
Adaptive Gradient Quantization for Data-Parallel SGD
Finite Continuum-Armed Bandits
Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies
Compact task representations as a normative model for higher-order brain activity
Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs
Co-exposure Maximization in Online Social Networks
UCLID-Net: Single View Reconstruction in Object Space
Reinforcement Learning for Control with Multiple Frequencies
Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval
Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs
A Unified View of Label Shift Estimation
Optimal Private Median Estimation under Minimal Distributional Assumptions
Breaking the Communication-Privacy-Accuracy Trilemma
Audeo: Audio Generation for a Silent Performance Video
Ode to an ODE
Self-Distillation Amplifies Regularization in Hilbert Space
Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators
Community detection using fast low-cardinality semidefinite programming 
Modeling Noisy Annotations for Crowd Counting
An operator view of policy gradient methods
Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases
Online MAP Inference of Determinantal Point Processes
Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement
Inferring learning rules from animal decision-making
Input-Aware Dynamic Backdoor Attack
How hard is to distinguish graphs with graph neural networks?
Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transition
Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks
Cross-Scale Internal Graph Neural Network for Image Super-Resolution
Unsupervised Representation Learning by Invariance Propagation
Restoring Negative Information in Few-Shot Object Detection
Do Adversarially Robust ImageNet Models Transfer Better?
Robust Correction of Sampling Bias using Cumulative Distribution Functions
Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach
Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
Classification with Valid and Adaptive Coverage
Learning Global Transparent Models consistent with Local Contrastive Explanations
Learning to Approximate a Bregman Divergence
Diverse Image Captioning with Context-Object Split Latent Spaces
Learning Disentangled Representations of Videos with Missing Data
Natural Graph Networks
Continual Learning with Node-Importance based Adaptive Group Sparse Regularization
Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts
Bidirectional Convolutional Poisson Gamma Dynamical Systems
Deep Reinforcement and InfoMax Learning
On ranking via sorting by estimated expected utility
Distribution-free binary classification: prediction sets, confidence intervals and calibration
Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow
Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals
Variance reduction for Random Coordinate Descent-Langevin Monte Carlo
Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration
All Word Embeddings from One Embedding
Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm
How to Characterize The Landscape of Overparameterized Convolutional Neural Networks
On the Tightness of Semidefinite Relaxations for Certifying Robustness to Adversarial Examples
Submodular Meta-Learning
Rethinking Pre-training and Self-training
Unsupervised Sound Separation Using Mixture Invariant Training
Adaptive Discretization for Model-Based Reinforcement Learning
CodeCMR: Cross-Modal Retrieval For Function-Level Binary Source Code Matching
On Warm-Starting Neural Network Training
DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks
OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification
An Imitation from Observation Approach to Transfer Learning with Dynamics Mismatch
Learning About Objects by Learning to Interact with Them
Learning discrete distributions with infinite support
Dissecting Neural ODEs
Teaching a GAN What Not to Learn
Counterfactual Data Augmentation using Locally Factored Dynamics
Rethinking Learnable Tree Filter for Generic Feature Transform
Self-Supervised Relational Reasoning for Representation Learning
Sufficient dimension reduction for classification using principal optimal transport direction
Fast Epigraphical Projection-based Incremental Algorithms for Wasserstein Distributionally Robust Support Vector Machine
Differentially Private Clustering: Tight Approximation Ratios
On the Power of Louvain in the Stochastic Block Model
Fairness with Overlapping Groups; a Probabilistic Perspective
AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control
Searching for Low-Bit Weights in Quantized Neural Networks
Adaptive Reduced Rank Regression
From Predictions to Decisions: Using Lookahead Regularization
Sequential Bayesian Experimental Design with Variable Cost Structure
Predictive inference is free with the jackknife±after-bootstrap
Counterfactual Predictions under Runtime Confounding
Learning Loss for Test-Time Augmentation
Balanced Meta-Softmax for Long-Tailed Visual Recognition
Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization
MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods
On the Error Resistance of Hinge-Loss Minimization
Munchausen Reinforcement Learning
Object Goal Navigation using Goal-Oriented Semantic Exploration
Efficient semidefinite-programming-based inference for binary and multi-class MRFs
Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing
Semantic Visual Navigation by Watching YouTube Videos
Heavy-tailed Representations, Text Polarity Classification & Data Augmentation
SuperLoss: A Generic Loss for Robust Curriculum Learning
CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models
Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards
Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations
Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms
Learning Differential Equations that are Easy to Solve
Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses
Influence-Augmented Online Planning for Complex Environments
PAC-Bayes Learning Bounds for Sample-Dependent Priors
Reward-rational (implicit) choice: A unifying formalism for reward learning
Probabilistic Time Series Forecasting with Shape and Temporal Diversity
Low Distortion Block-Resampling with Spatially Stochastic Networks
Continual Deep Learning by Functional Regularisation of Memorable Past
Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning
Fast Fourier Convolution
Unsupervised Learning of Dense Visual Representations
Higher-Order Certification For Randomized Smoothing
Learning Structured Distributions From Untrusted Batches: Faster and Simpler
Hierarchical Quantized Autoencoders
Diversity can be Transferred: Output Diversification for White- and Black-box Attacks
POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis
AvE: Assistance via Empowerment
Variational Policy Gradient Method for Reinforcement Learning with General Utilities
Reverse-engineering recurrent neural network solutions to a hierarchical inference task for mice
Temporal Positive-unlabeled Learning for Biomedical Hypothesis Generation via Risk Estimation
Efficient Low Rank Gaussian Variational Inference for Neural Networks
Privacy Amplification via Random Check-Ins
Probabilistic Circuits for Variational Inference in Discrete Graphical Models
Your Classifier can Secretly Suffice Multi-Source Domain Adaptation
Labelling unlabelled videos from scratch with multi-modal self-supervision
A Non-Asymptotic Analysis for Stein Variational Gradient Descent
Robust Meta-learning for Mixed Linear Regression with Small Batches
Bayesian Deep Learning and a Probabilistic Perspective of Generalization
Unsupervised Learning of Object Landmarks via Self-Training Correspondence
Randomized tests for high-dimensional regression: A more efficient and powerful solution
Learning Representations from Audio-Visual Spatial Alignment
Generative View Synthesis: From Single-view Semantics to Novel-view Images
Towards More Practical Adversarial Attacks on Graph Neural Networks
Multi-Task Reinforcement Learning with Soft Modularization
Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models
On the training dynamics of deep networks with  L 2 L_2 L2​ regularization
Improved Algorithms for Convex-Concave Minimax Optimization
Deep Variational Instance Segmentation
Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence
Deep Multimodal Fusion by Channel Exchanging
Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems
AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity
Delay and Cooperation in Nonstochastic Linear Bandits
Probabilistic Orientation Estimation with Matrix Fisher Distributions
Minimax Dynamics of Optimally Balanced Spiking Networks of Excitatory and Inhibitory Neurons
Telescoping Density-Ratio Estimation
Towards Deeper Graph Neural Networks with Differentiable Group Normalization
Stochastic Optimization for Performative Prediction
Learning Differentiable Programs with Admissible Neural Heuristics
Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nystrom method
Domain Adaptation as a Problem of Inference on Graphical Models
Network size and size of the weights in memorization with two-layers neural networks
Certifying Strategyproof Auction Networks
Continual Learning of Control Primitives : Skill Discovery via Reset-Games
HOI Analysis: Integrating and Decomposing Human-Object Interaction
Strongly local p-norm-cut algorithms for semi-supervised learning and local graph clustering
Deep Direct Likelihood Knockoffs
Meta-Neighborhoods
Neural Dynamic Policies for End-to-End Sensorimotor Learning
A new inference approach for training shallow and deep generalized linear models of noisy interacting neurons
Decision-Making with Auto-Encoding Variational Bayes
Attribution Preservation in Network Compression for Reliable Network Interpretation
Feature Importance Ranking for Deep Learning
Causal Estimation with Functional Confounders
Model Inversion Networks for Model-Based Optimization
Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks
Exact expressions for double descent and implicit regularization via surrogate random design
Certifying Confidence via Randomized Smoothing
Learning Physical Constraints with Neural Projections
Robust Optimization for Fairness with Noisy Protected Groups
Noise-Contrastive Estimation for Multivariate Point Processes
A Game-Theoretic Analysis of the Empirical Revenue Maximization Algorithm with Endogenous Sampling
Neural Path Features and Neural Path Kernel : Understanding the role of gates in deep learning
Multiscale Deep Equilibrium Models
Sparse Graphical Memory for Robust Planning
Second Order PAC-Bayesian Bounds for the Weighted Majority Vote
Dirichlet Graph Variational Autoencoder
Modeling Task Effects on Meaning Representation in the Brain via Zero-Shot MEG Prediction
Counterfactual Vision-and-Language Navigation: Unravelling the Unseen
Robust Quantization: One Model to Rule Them All
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Federated Accelerated Stochastic Gradient Descent
Robust Density Estimation under Besov IPM Losses
An analytic theory of shallow networks dynamics for hinge loss classification
Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithm
Learning to Orient Surfaces by Self-supervised Spherical CNNs
Adam with Bandit Sampling for Deep Learning
Parabolic Approximation Line Search for DNNs
Agnostic Learning of a Single Neuron with Gradient Descent
Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits
Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry
Generative causal explanations of black-box classifiers
Sub-sampling for Efficient Non-Parametric Bandit Exploration
Learning under Model Misspecification: Applications to Variational and Ensemble methods
Language Through a Prism: A Spectral Approach for Multiscale Language Representations
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
Towards practical differentially private causal graph discovery
Independent Policy Gradient Methods for Competitive Reinforcement Learning
The Value Equivalence Principle for Model-Based Reinforcement Learning
Structured Convolutions for Efficient Neural Network Design
Latent World Models For Intrinsically Motivated Exploration
Estimating Rank-One Spikes from Heavy-Tailed Noise via Self-Avoiding Walks
Policy Improvement via Imitation of Multiple Oracles
Training Generative Adversarial Networks by Solving Ordinary Differential Equations
Learning of Discrete Graphical Models with Neural Networks
RepPoints v2: Verification Meets Regression for Object Detection
Unfolding the Alternating Optimization for Blind Super Resolution
Entrywise convergence of iterative methods for eigenproblems
Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views
A Catalyst Framework for Minimax Optimization
Self-supervised Co-Training for Video Representation Learning
Gradient Estimation with Stochastic Softmax Tricks
Meta-Learning Requires Meta-Augmentation
SLIP: Learning to predict in unknown dynamical systems with long-term memory
Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
Bayesian Bits: Unifying Quantization and Pruning
On Testing of Samplers
Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective
MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization
Woodbury Transformations for Deep Generative Flows
Graph Contrastive Learning with Augmentations
Gradient Surgery for Multi-Task Learning
Bayesian Probabilistic Numerical Integration with Tree-Based Models
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel
Graph Meta Learning via Local Subgraphs
Stochastic Deep Gaussian Processes over Graphs
Bayesian Causal Structural Learning with Zero-Inflated Poisson Bayesian Networks
Evaluating Attribution for Graph Neural Networks
On Second Order Behaviour in Augmented Neural ODEs
Neuron Shapley: Discovering the Responsible Neurons
Stochastic Normalizing Flows
GPU-Accelerated Primal Learning for Extremely Fast Large-Scale Classification
Random Reshuffling is Not Always Better
Model Agnostic Multilevel Explanations
NeuMiss networks: differentiable programming for supervised learning with missing values.
Revisiting Parameter Sharing for Automatic Neural Channel Number Search
Differentially-Private Federated Linear Bandits
Is Plug-in Solver Sample-Efficient for Feature-based Reinforcement Learning?
Learning Physical Graph Representations from Visual Scenes
Deep Graph Pose: a semi-supervised deep graphical model for improved animal pose tracking
Meta-learning from Tasks with Heterogeneous Attribute Spaces
Estimating decision tree learnability with polylogarithmic sample complexity
Sparse Symplectically Integrated Neural Networks
Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision
Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence
Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension
Predicting Training Time Without Training 
How does This Interaction Affect Me? Interpretable Attribution for Feature Interactions
Optimal Adaptive Electrode Selection to Maximize Simultaneously Recorded Neuron Yield
Neurosymbolic Reinforcement Learning with Formally Verified Exploration
Wavelet Flow: Fast Training of High Resolution Normalizing Flows
Multi-task Batch Reinforcement Learning with Metric Learning
On 1/n neural representation and robustness
Boundary thickness and robustness in learning models
Demixed shared component analysis of neural population data from multiple brain areas
Learning Kernel Tests Without Data Splitting
Unsupervised Data Augmentation for Consistency Training
Subgroup-based Rank-1 Lattice Quasi-Monte Carlo
Minibatch vs Local SGD for Heterogeneous Distributed Learning
Multi-task Causal Learning with Gaussian Processes
Proximity Operator of the Matrix Perspective Function and its Applications
Generative 3D Part Assembly via Dynamic Graph Learning
Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention
The Power of Comparisons for Actively Learning Linear Classifiers
From Boltzmann Machines to Neural Networks and Back Again
Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality
Pruning neural networks without any data by iteratively conserving synaptic flow
Detecting Interactions from Neural Networks via Topological Analysis
Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systems
Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations
Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes
Benchmarking Deep Learning Interpretability in Time Series Predictions
Federated Principal Component Analysis
(De)Randomized Smoothing for Certifiable Defense against Patch Attacks
SMYRF - Efficient Attention using Asymmetric Clustering
Introducing Routing Uncertainty in Capsule Networks
A Simple and Efficient Smoothing Method for Faster Optimization and Local Exploration
Hyperparameter Ensembles for Robustness and Uncertainty Quantification
Neutralizing Self-Selection Bias in Sampling for Sortition
On the Convergence of Smooth Regularized Approximate Value Iteration Schemes
Off-Policy Evaluation via the Regularized Lagrangian
The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning
Neural Power Units
Towards Scalable Bayesian Learning of Causal DAGs
A Dictionary Approach to Domain-Invariant Learning in Deep Networks
Bootstrapping neural processes
Large-Scale Adversarial Training for Vision-and-Language Representation Learning
Most ReLU Networks Suffer from  ℓ 2 \ell^2 ℓ2 Adversarial Perturbations
Compositional Visual Generation with Energy Based Models
Factor Graph Grammars
Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs
Autoregressive Score Matching
Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization
Neural Controlled Differential Equations for Irregular Time Series
On Efficiency in Hierarchical Reinforcement Learning
On Correctness of Automatic Differentiation for Non-Differentiable Functions
Probabilistic Linear Solvers for Machine Learning
Dynamic Regret of Policy Optimization in Non-Stationary Environments
Multipole Graph Neural Operator for Parametric Partial Differential Equations
BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images
Online Structured Meta-learning
Learning Strategic Network Emergence Games
Towards Interpretable Natural Language Understanding with Explanations as Latent Variables
The Mean-Squared Error of Double Q-Learning
What Makes for Good Views for Contrastive Learning?
Denoising Diffusion Probabilistic Models
Barking up the right tree: an approach to search over molecule synthesis DAGs
On Uniform Convergence and Low-Norm Interpolation Learning
Bandit Samplers for Training Graph Neural Networks
Sampling from a k-DPP without looking at all items
Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence
Hierarchical Poset Decoding for Compositional Generalization in Language
Evaluating and Rewarding Teamwork Using Cooperative Game Abstractions
Exchangeable Neural ODE for Set Modeling
Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Distributions
CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection
Regularized linear autoencoders recover the principal components, eventually
Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization
GramGAN: Deep 3D Texture Synthesis From 2D Exemplars
UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection
Learning Restricted Boltzmann Machines with Sparse Latent Variables
Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction
Curriculum learning for multilevel budgeted combinatorial problems
FedSplit: an algorithmic framework for fast federated optimization
Estimation and Imputation in Probabilistic Principal Component Analysis with Missing Not At Random Data
Correlation Robust Influence Maximization
Neuronal Gaussian Process Regression
Nonconvex Sparse Graph Learning under Laplacian Constrained Graphical Model
Synthetic Data Generators – Sequential and Private
Uncertainty Quantification for Inferring Hawkes Networks
Implicit Distributional Reinforcement Learning
Auxiliary Task Reweighting for Minimum-data Learning
Small Nash Equilibrium Certificates in Very Large Games
Training Linear Finite-State Machines
Efficient active learning of sparse halfspaces with arbitrary bounded noise
Swapping Autoencoder for Deep Image Manipulation
Self-Supervised Few-Shot Learning on Point Clouds
Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC
Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE
RL Unplugged: A Collection of Benchmarks for Offline Reinforcement Learning
Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning
Interior Point Solving for LP-based prediction+optimisation
A simple normative network approximates local non-Hebbian learning in the cortex
Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks
Understanding the Role of Training Regimes in Continual Learning
Fair regression with Wasserstein barycenters
Training Stronger Baselines for Learning to Optimize
Exactly Computing the Local Lipschitz Constant of ReLU Networks
Strictly Batch Imitation Learning by Energy-based Distribution Matching
On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method
A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems
Generating Correct Answers for Progressive Matrices Intelligence Tests
HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss
Preference learning along multiple criteria: A game-theoretic perspective
Multi-Plane Program Induction with 3D Box Priors
Online Neural Connectivity Estimation with Noisy Group Testing
Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free
Implicit Neural Representations with Periodic Activation Functions
Rotated Binary Neural Network
Community detection in sparse time-evolving graphs with a dynamical Bethe-Hessian
Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness
Adaptive Learning of Rank-One Models for Efficient Pairwise Sequence Alignment
Hierarchical nucleation in deep neural networks
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
Graph Geometry Interaction Learning
Differentiable Augmentation for Data-Efficient GAN Training
Heuristic Domain Adaptation
Learning Certified Individually Fair Representations
Part-dependent Label Noise: Towards Instance-dependent Label Noise
Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods
Geometric Exploration for Online Control
Automatic Curriculum Learning through Value Disagreement
MRI Banding Removal via Adversarial Training
The NetHack Learning Environment
Language and Visual Entity Relationship Graph for Agent Navigation
ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping
Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks
No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium
Estimating weighted areas under the ROC curve
Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study
Generalized Hindsight for Reinforcement Learning
Critic Regularized Regression
Boosting Adversarial Training with Hypersphere Embedding
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows
Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent
Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification
Detecting Hands and Recognizing Physical Contact in the Wild
On the Theory of Transfer Learning: The Importance of Task Diversity
Finite-Time Analysis of Round-Robin Kullback-Leibler Upper Confidence Bounds for Optimal Adaptive Allocation with Multiple Plays and Markovian Rewards
Neural Star Domain as Primitive Representation
Off-Policy Interval Estimation with Lipschitz Value Iteration
Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics
Deep Statistical Solvers
Distributionally Robust Parametric Maximum Likelihood Estimation
Secretary and Online Matching Problems with Machine Learned Advice
Deep Transformation-Invariant Clustering
Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree
Improving Generalization in Reinforcement Learning with Mixture Regularization
Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework
Learning from Aggregate Observations
The Devil is in the Detail: A Framework for Macroscopic Prediction via Microscopic Models
Subgraph Neural Networks
Demystifying Orthogonal Monte Carlo and Beyond
Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms
A Scalable Approach for Privacy-Preserving Collaborative Machine Learning
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
Towards Learning Convolutions from Scratch
Cycle-Contrast for Self-Supervised Video Representation Learning
Posterior Re-calibration for Imbalanced Datasets
Novelty Search in Representational Space for Sample Efficient Exploration
Robust Reinforcement Learning via Adversarial training with Langevin Dynamics
Adversarial Blocking Bandits
Online Algorithms for Multi-shop Ski Rental with Machine Learned Advice
Multi-label Contrastive Predictive Coding
Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud
Learning Invariants through Soft Unification
One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL
Variational Bayesian Monte Carlo with Noisy Likelihoods
Finite-Sample Analysis of Contractive Stochastic Approximation Using Smooth Convex Envelopes
Self-Supervised Generative Adversarial Compression
An efficient nonconvex reformulation of stagewise convex optimization problems
From Finite to Countable-Armed Bandits
Adversarial Distributional Training for Robust Deep Learning
Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes
Theory-Inspired Path-Regularized Differential Network Architecture Search
Conic Descent and its Application to Memory-efficient Optimization over Positive Semidefinite Matrices
Learning the Geometry of Wave-Based Imaging
Greedy inference with structure-exploiting lazy maps
Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning
Finding the Homology of Decision Boundaries with Active Learning
Reinforced Molecular Optimization with Neighborhood-Controlled Grammars
Natural Policy Gradient Primal-Dual Method for Constrained Markov Decision Processes
Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Evolvability
Certified Defense to Image Transformations via Randomized Smoothing
Estimation of Skill Distribution from a Tournament
Reparameterizing Mirror Descent as Gradient Descent
General Control Functions for Causal Effect Estimation from IVs
Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards
Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks
Zero-Resource Knowledge-Grounded Dialogue Generation
Targeted Adversarial Perturbations for Monocular Depth Prediction
Beyond the Mean-Field: Structured Deep Gaussian Processes Improve the Predictive Uncertainties
Offline Imitation Learning with a Misspecified Simulator
Multi-Fidelity Bayesian Optimization via Deep Neural Networks
PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals
Bad Global Minima Exist and SGD Can Reach Them
Optimal Prediction of the Number of Unseen Species with Multiplicity
Characterizing Optimal Mixed Policies: Where to Intervene and What to Observe
Factor Graph Neural Networks
A Closer Look at Accuracy vs. Robustness
Curriculum Learning by Dynamic Instance Hardness
Spin-Weighted Spherical CNNs
Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference
Baxter Permutation Process
Characterizing emergent representations in a space of candidate learning rules for deep networks
Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation
Adaptive Probing Policies for Shortest Path Routing
Approximate Heavily-Constrained Learning with Lagrange Multiplier Models
Faster Randomized Infeasible Interior Point Methods for Tall/Wide Linear Programs
Sliding Window Algorithms for k-Clustering Problems
AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
Approximate Cross-Validation for Structured Models
Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation
Debiased Contrastive Learning
UCSG-NET- Unsupervised Discovering of Constructive Solid Geometry Tree
Generalized Boosting
COT-GAN: Generating Sequential Data via Causal Optimal Transport
Impossibility Results for Grammar-Compressed Linear Algebra
Understanding spiking networks through convex optimization
Better Full-Matrix Regret via Parameter-Free Online Learning
Large-Scale Methods for Distributionally Robust Optimization
Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring
Bandit Linear Control
Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals
PEP: Parameter Ensembling by Perturbation
Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View
Adversarial Example Games
Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts
Provably Efficient Neural Estimation of Structural Equation Models: An Adversarial Approach
Security Analysis of Safe and Seldonian Reinforcement Learning Algorithms
Learning to Play Sequential Games versus Unknown Opponents
Further Analysis of Outlier Detection with Deep Generative Models
Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning
Neural Networks Learning and Memorization with (almost) no Over-Parameterization
Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits
Towards a Combinatorial Characterization of Bounded-Memory Learning
Chaos, Extremism and Optimism: Volume Analysis of Learning in Games
On Regret with Multiple Best Arms
Matrix Completion with Hierarchical Graph Side Information
Is Long Horizon RL More Difficult Than Short Horizon RL?
Hamiltonian Monte Carlo using an adjoint-differentiated Laplace approximation: Bayesian inference for latent Gaussian models and beyond
Adversarial Learning for Robust Deep Clustering
Learning Mutational Semantics
Learning to Learn Variational Semantic Memory
Myersonian Regression
Learnability with Indirect Supervision Signals
Towards Safe Policy Improvement for Non-Stationary MDPs
Finer Metagenomic Reconstruction via Biodiversity Optimization
Causal Discovery in Physical Systems from Videos
Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data
Smoothed Analysis of Online and Differentially Private Learning
Self-Paced Deep Reinforcement Learning
Kalman Filtering Attention for User Behavior Modeling in CTR Prediction
Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples
Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels
GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction
Optimal visual search based on a model of target detectability in natural images
Towards Convergence Rate Analysis of Random Forests for Classification
List-Decodable Mean Estimation via Iterative Multi-Filtering
Exact Recovery of Mangled Clusters with Same-Cluster Queries
Steady State Analysis of Episodic Reinforcement Learning
Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures
Bayesian Optimization for Iterative Learning
Minimax Bounds for Generalized Linear Models
Projection Robust Wasserstein Distance and Riemannian Optimization
CoinDICE: Off-Policy Confidence Interval Estimation
Simple and Fast Algorithm for Binary Integer and Online Linear Programming
Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction
Learning Rich Rankings
Color Visual Illusions: A Statistics-based Computational Model
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Universal guarantees for decision tree induction via a higher-order splitting criterion
Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation
A Boolean Task Algebra for Reinforcement Learning
Learning with Differentiable Pertubed Optimizers
Optimal Learning from Verified Training Data
Online Linear Optimization with Many Hints
Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification
Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning
Exploiting the Surrogate Gap in Online Multiclass Classification
The Pitfalls of Simplicity Bias in Neural Networks
Automatically Learning Compact Quality-aware Surrogates for Optimization Problems
Empirical Likelihood for Contextual Bandits
Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?
Non-reversible Gaussian processes for identifying latent dynamical structure in neural data
Listening to Sounds of Silence for Speech Denoising
BoxE: A Box Embedding Model for Knowledge Base Completion
Coherent Hierarchical Multi-Label Classification Networks
Walsh-Hadamard Variational Inference for Bayesian Deep Learning
Federated Bayesian Optimization via Thompson Sampling
MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation
Neural Complexity Measures
Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform
Provably adaptive reinforcement learning in metric spaces
ShapeFlow: Learnable Deformation Flows Among 3D Shapes
Self-Supervised Learning by Cross-Modal Audio-Video Clustering
Optimal Query Complexity of Secure Stochastic Convex Optimization
DynaBERT: Dynamic BERT with Adaptive Width and Depth
Generalization Bound of Gradient Descent for Non-Convex Metric Learning
Dynamic Submodular Maximization
Inference for Batched Bandits
Approximate Cross-Validation with Low-Rank Data in High Dimensions
GANSpace: Discovering Interpretable GAN Controls
Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization
Neuron-level Structured Pruning using Polarization Regularizer
Limits on Testing Structural Changes in Ising Models
Field-wise Learning for Multi-field Categorical Data
Continual Learning in Low-rank Orthogonal Subspaces
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms
Learning Deformable Tetrahedral Meshes for 3D Reconstruction
Information theoretic limits of learning a sparse rule
Self-supervised learning through the eyes of a child
Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning
A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning
What shapes feature representations? Exploring datasets, architectures, and training
Optimal Best-arm Identification in Linear Bandits
Data Diversification: A Simple Strategy For Neural Machine Translation
Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding
CoSE: Compositional Stroke Embeddings
Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks
Biological credit assignment through dynamic inversion of feedforward networks
Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching
Learning Multi-Agent Communication through Structured Attentive Reasoning
Private Identity Testing for High-Dimensional Distributions
On the Optimal Weighted  ℓ 2 \ell_2 ℓ2​ Regularization in Overparameterized Linear Regression
An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search
MetaSDF: Meta-Learning Signed Distance Functions
Simple and Scalable Sparse k-means Clustering via Feature Ranking
Model-based Adversarial Meta-Reinforcement Learning
Graph Policy Network for Transferable Active Learning on Graphs
Towards a Better Global Loss Landscape of GANs
Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed Bandits
UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging
Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders
An Unbiased Risk Estimator for Learning with Augmented Classes
AutoBSS: An Efficient Algorithm for Block Stacking Style Search
Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point
Stochastic Optimization with Laggard Data Pipelines
Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
GPS-Net: Graph-based Photometric Stereo Network
Consistent Structural Relation Learning for Zero-Shot Segmentation
Model Selection in Contextual Stochastic Bandit Problems
Truncated Linear Regression in High Dimensions
Incorporating Pragmatic Reasoning Communication into Emergent Language
Deep Subspace Clustering with Data Augmentation
An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits
Can Graph Neural Networks Count Substructures?
A Bayesian Perspective on Training Speed and Model Selection
On the Modularity of Hypernetworks
Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies
Provably Efficient Neural GTD for Off-Policy Learning
Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
Stable and expressive recurrent vision models
Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form
BRP-NAS: Prediction-based NAS using GCNs
Deep Shells: Unsupervised Shape Correspondence with Optimal Transport
ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding
Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D
Regularizing Black-box Models for Improved Interpretability
Trust the Model When It Is Confident: Masked Model-based Actor-Critic
Semi-Supervised Neural Architecture Search
Consistency Regularization for Certified Robustness of Smoothed Classifiers
Robust Multi-Agent Reinforcement Learning with Model Uncertainty
SIRI: Spatial Relation Induced Network For Spatial Description Resolution
Adaptive Shrinkage Estimation for Streaming Graphs
Make One-Shot Video Object Segmentation Efficient Again
Depth Uncertainty in Neural Networks
Non-Euclidean Universal Approximation
Constraining Variational Inference with Geometric Jensen-Shannon Divergence
Gibbs Sampling with People
HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory
FrugalML: How to use ML Prediction APIs more accurately and cheaply
Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth
Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning
Monotone operator equilibrium networks
When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes
Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control
High-Dimensional Sparse Linear Bandits
Non-Stochastic Control with Bandit Feedback
Generalized Leverage Score Sampling for Neural Networks
An Optimal Elimination Algorithm for Learning a Best Arm
Efficient Projection-free Algorithms for Saddle Point Problems
A mathematical model for automatic differentiation in machine learning
Unsupervised Text Generation by Learning from Search
Learning Compositional Rules via Neural Program Synthesis
Incorporating BERT into Parallel Sequence Decoding with Adapters
Estimating Fluctuations in Neural Representations of Uncertain Environments
Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation
SURF: A Simple, Universal, Robust, Fast Distribution Learning Algorithm
Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks
General Transportability of Soft Interventions: Completeness Results
GAIT-prop: A biologically plausible learning rule derived from backpropagation of error
Lipschitz Bounds and Provably Robust Training by Laplacian Smoothing
SCOP: Scientific Control for Reliable Neural Network Pruning
Provably Consistent Partial-Label Learning
Robust, Accurate Stochastic Optimization for Variational Inference
Discovering conflicting groups in signed networks
Learning Some Popular Gaussian Graphical Models without Condition Number Bounds
Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding
Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions
Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition
VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain
The Smoothed Possibility of Social Choice
A Decentralized Parallel Algorithm for Training Generative Adversarial Nets
Phase retrieval in high dimensions: Statistical and computational phase transitions
Fair Performance Metric Elicitation
Hybrid Variance-Reduced SGD Algorithms For Minimax Problems with Nonconvex-Linear Function
Belief-Dependent Macro-Action Discovery in POMDPs using the Value of Information
Soft Contrastive Learning for Visual Localization
Fine-Grained Dynamic Head for Object Detection
LoCo: Local Contrastive Representation Learning
Modeling and Optimization Trade-off in Meta-learning
SnapBoost: A Heterogeneous Boosting Machine
On Adaptive Distance Estimation
Stage-wise Conservative Linear Bandits
RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
Metric-Free Individual Fairness in Online Learning
GreedyFool: Distortion-Aware Sparse Adversarial Attack
VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data
RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist
Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining
Improved Sample Complexity for Incremental Autonomous Exploration in MDPs
TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning
RD 2 ^2 2: Reward Decomposition with Representation Decomposition
Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
Fairness constraints can help exact inference in structured prediction
Instance-based Generalization in Reinforcement Learning
Smooth And Consistent Probabilistic Regression Trees
Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programming
Factorized Neural Processes for Neural Processes: K-Shot Prediction of Neural Responses
Winning the Lottery with Continuous Sparsification
Adversarial robustness via robust low rank representations
Joints in Random Forests
Compositional Generalization by Learning Analytical Expressions
JAX MD: A Framework for Differentiable Physics
An implicit function learning approach for parametric modal regression
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
Coresets for Robust Training of Deep Neural Networks against Noisy Labels
Adapting to Misspecification in Contextual Bandits
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
Learning to solve TV regularised problems with unrolled algorithms
Object-Centric Learning with Slot Attention
Improving robustness against common corruptions by covariate shift adaptation
Deep Smoothing of the Implied Volatility Surface
Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations
Provable Online CP/PARAFAC Decomposition of a Structured Tensor via Dictionary Learning
Look-ahead Meta Learning for Continual Learning
A polynomial-time algorithm for learning nonparametric causal graphs
Sparse Learning with CART
Proximal Mapping for Deep Regularization
Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models
Hierarchical Granularity Transfer Learning
Deep active inference agents using Monte-Carlo methods
Consistent Estimation of Identifiable Nonparametric Mixture Models from Grouped Observations
Manifold structure in graph embeddings
Adaptive Learned Bloom Filter (Ada-BF): Efficient Utilization of the Classifier with Application to Real-Time Information Filtering on the Web
MCUNet: Tiny Deep Learning on IoT Devices
In search of robust measures of generalization
Task-agnostic Exploration in Reinforcement Learning
Multi-task Additive Models for Robust Estimation and Automatic Structure Discovery
Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration
Softmax Deep Double Deterministic Policy Gradients
Online Decision Based Visual Tracking via Reinforcement Learning
Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity
DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs
Distributional Robustness with IPMs and links to Regularization and GANs
A shooting formulation of deep learning
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning
MATE: Plugging in Model Awareness to Task Embedding for Meta Learning
Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits
Predictive Information Accelerates Learning in RL
Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization
High-Fidelity Generative Image Compression
A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning
Counterexample-Guided Learning of Monotonic Neural Networks
A Novel Approach for Constrained Optimization in Graphical Models
Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology
On the Trade-off between Adversarial and Backdoor Robustness
Implicit Graph Neural Networks
Rethinking Importance Weighting for Deep Learning under Distribution Shift
Guiding Deep Molecular Optimization with Genetic Exploration
Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks
TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation
Neural Topographic Factor Analysis for fMRI Data
Neural Architecture Generator Optimization
A Bandit Learning Algorithm and Applications to Auction Design
MetaPoison: Practical General-purpose Clean-label Data Poisoning
Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation
Training Generative Adversarial Networks with Limited Data
Deeply Learned Spectral Total Variation Decomposition
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
Improving Neural Network Training in Low Dimensional Random Bases
Safe Reinforcement Learning via Curriculum Induction
Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning
How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?
Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses
Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method
PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks
Few-Cost Salient Object Detection with Adversarial-Paced Learning
Minimax Estimation of Conditional Moment Models
Causal Imitation Learning With Unobserved Confounders
Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling
Learning Black-Box Attackers with Transferable Priors and Query Feedback
Locally Differentially Private (Contextual) Bandits Learning
Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax
Kernel Based Progressive Distillation for Adder Neural Networks
Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization
Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space
The Wasserstein Proximal Gradient Algorithm
Universally Quantized Neural Compression
Temporal Variability in Implicit Online Learning
Investigating Gender Bias in Language Models Using Causal Mediation Analysis
Off-Policy Imitation Learning from Observations
Escaping Saddle-Point Faster under Interpolation-like Conditions
Matérn Gaussian Processes on Riemannian Manifolds
Improved Techniques for Training Score-Based Generative Models
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
A Maximum-Entropy Approach to Off-Policy Evaluation in Average-Reward MDPs
Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients
Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
Value-driven Hindsight Modelling
Dynamic Regret of Convex and Smooth Functions
On Convergence of Nearest Neighbor Classifiers over Feature Transformations
Mitigating Manipulation in Peer Review via Randomized Reviewer Assignments
Contrastive learning of global and local features for medical image segmentation with limited annotations
Self-Supervised Graph Transformer on Large-Scale Molecular Data
Generative Neurosymbolic Machines
How many samples is a good initial point worth in Low-rank Matrix Recovery?
CSER: Communication-efficient SGD with Error Reset
Efficient estimation of neural tuning during naturalistic behavior
High-recall causal discovery for autocorrelated time series with latent confounders
Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes
Joint Contrastive Learning with Infinite Possibilities
Robust Gaussian Covariance Estimation in Nearly-Matrix Multiplication Time
Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models
GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators
SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
Learning Causal Effects via Weighted Empirical Risk Minimization
Revisiting the Sample Complexity of Sparse Spectrum Approximation of Gaussian Processes
Incorporating Interpretable Output Constraints in Bayesian Neural Networks
Multi-Stage Influence Function
Probabilistic Fair Clustering
Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA
Testing Determinantal Point Processes
CogLTX: Applying BERT to Long Texts
f-GAIL: Learning f-Divergence for Generative Adversarial Imitation Learning
Non-parametric Models for Non-negative Functions
Uncertainty Aware Semi-Supervised Learning on Graph Data
ConvBERT: Improving BERT with Span-based Dynamic Convolution
Practical No-box Adversarial Attacks against DNNs
Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model
Walking in the Shadow: A New Perspective on Descent Directions for Constrained Minimization
Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks
Reward Propagation Using Graph Convolutional Networks
LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration
Fully Dynamic Algorithm for Constrained Submodular Optimization
Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation
Autofocused oracles for model-based design
Debiasing Averaged Stochastic Gradient Descent to handle missing values
Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning
CompRess: Self-Supervised Learning by Compressing Representations
Sample complexity and effective dimension for regression on manifolds
The phase diagram of approximation rates for deep neural networks
Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network
EcoLight: Intersection Control in Developing Regions Under Extreme Budget and Network Constraints
Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN
Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design
A Spectral Energy Distance for Parallel Speech Synthesis
Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations
Learning from Positive and Unlabeled Data with Arbitrary Positive Shift
Deep Energy-based Modeling of Discrete-Time Physics
Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning
Self-Learning Transformations for Improving Gaze and Head Redirection
Language-Conditioned Imitation Learning for Robot Manipulation Tasks
POMDPs in Continuous Time and Discrete Spaces
Exemplar Guided Active Learning
Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Grasps
Node Embeddings and Exact Low-Rank Representations of Complex Networks
Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications
Steering Distortions to Preserve Classes and Neighbors in Supervised Dimensionality Reduction
On Infinite-Width Hypernetworks
Interferobot: aligning an optical interferometer by a reinforcement learning agent
Program Synthesis with Pragmatic Communication
Principal Neighbourhood Aggregation for Graph Nets
Reliable Graph Neural Networks via Robust Aggregation
Instance Selection for GANs
Linear Disentangled Representations and Unsupervised Action Estimation
Video Frame Interpolation without Temporal Priors
Learning compositional functions via multiplicative weight updates
Sample Complexity of Uniform Convergence for Multicalibration
Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement
The interplay between randomness and structure during learning in RNNs
A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks
Instance-wise Feature Grouping
Robust Disentanglement of a Few Factors at a Time
PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning
Group Contextual Encoding for 3D Point Clouds
Latent Bandits Revisited
Is normalization indispensable for training deep neural network? 
Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions
Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks
Linear Time Sinkhorn Divergences using Positive Features
VarGrad: A Low-Variance Gradient Estimator for Variational Inference
A Convolutional Auto-Encoder for Haplotype Assembly and Viral Quasispecies Reconstruction
Promoting Stochasticity for Expressive Policies via a Simple and Efficient Regularization Method
Adversarial Counterfactual Learning and Evaluation for Recommender System
Memory-Efficient Learning of Stable Linear Dynamical Systems for Prediction and Control
Evolving Normalization-Activation Layers
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
Efficient Learning of Discrete Graphical Models
Near-Optimal SQ Lower Bounds for Agnostically Learning Halfspaces and ReLUs under Gaussian Marginals
Neurosymbolic Transformers for Multi-Agent Communication
Fairness in Streaming Submodular Maximization: Algorithms and Hardness
Smoothed Geometry for Robust Attribution
Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms
Multi-agent active perception with prediction rewards
A Local Temporal Difference Code for Distributional Reinforcement Learning
Learning with Optimized Random Features: Exponential Speedup by Quantum Machine Learning without Sparsity and Low-Rank Assumptions
CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
Deep Automodulators
Convolutional Tensor-Train LSTM for Spatio-Temporal Learning
The Potts-Ising model for discrete multivariate data
Interpretable multi-timescale models for predicting fMRI responses to continuous natural speech
Group-Fair Online Allocation in Continuous Time
Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis
Understanding Gradient Clipping in Private SGD: A Geometric Perspective
O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers
Identifying signal and noise structure in neural population activity with Gaussian process factor models
Equivariant Networks for Hierarchical Structures
MinMax Methods for Optimal Transport and Beyond: Regularization, Approximation and Numerics
A Discrete Variational Recurrent Topic Model without the Reparametrization Trick
Transferable Graph Optimizers for ML Compilers
Learning with Operator-valued Kernels in Reproducing Kernel Krein Spaces
Learning Bounds for Risk-sensitive Learning
Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints
Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency
Provably Efficient Reinforcement Learning with Kernel and Neural Function Approximations
Constant-Expansion Suffices for Compressed Sensing with Generative Priors
RANet: Region Attention Network for Semantic Segmentation
A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent
Learning sparse codes from compressed representations with biologically plausible local wiring constraints
Self-Imitation Learning via Generalized Lower Bound Q-learning
Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity
Directional Pruning of Deep Neural Networks
Smoothly Bounding User Contributions in Differential Privacy 
Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping
Online Planning with Lookahead Policies
Learning Deep Attribution Priors Based On Prior Knowledge
Using noise to probe recurrent neural network structure and prune synapses
NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity
Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
Neural FFTs for Universal Texture Image Synthesis
Graph Cross Networks with Vertex Infomax Pooling
Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms
Calibration of Shared Equilibria in General Sum Partially Observable Markov Games
MOPO: Model-based Offline Policy Optimization
Building powerful and equivariant graph neural networks with structural message-passing
Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning
Practical Low-Rank Communication Compression in Decentralized Deep Learning
Mutual exclusivity as a challenge for deep neural networks
3D Shape Reconstruction from Vision and Touch
GradAug: A New Regularization Method for Deep Neural Networks
An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay
Learning Utilities and Equilibria in Non-Truthful Auctions
Rational neural networks
DISK: Learning local features with policy gradient
Transfer Learning via  ℓ 1 \ell_1 ℓ1​ Regularization
GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network
Deep Inverse Q-learning with Constraints
Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities
Prediction with Corrupted Expert Advice
Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency
Knowledge Augmented Deep Neural Networks for Joint Facial Expression and Action Unit Recognition
Point process models for sequence detection in high-dimensional neural spike trains
Adversarial Attacks on Linear Contextual Bandits
Meta-Consolidation for Continual Learning
Organizing recurrent network dynamics by task-computation to enable continual learning
Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting
Kernel Methods Through the Roof: Handling Billions of Points Efficiently
Spike and slab variational Bayes for high dimensional logistic regression
Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness
Fast geometric learning with symbolic matrices
MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler
CoinPress: Practical Private Mean and Covariance Estimation
Planning with General Objective Functions: Going Beyond Total Rewards
Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
KFC: A Scalable Approximation Algorithm for  k k k−center Fair Clustering
Leveraging Predictions in Smoothed Online Convex Optimization via Gradient-based Algorithms
Learning the Linear Quadratic Regulator from Nonlinear Observations
Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate
Scalable Graph Neural Networks via Bidirectional Propagation
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning
Assisted Learning: A Framework for Multi-Organization Learning
The Strong Screening Rule for SLOPE
STLnet: Signal Temporal Logic Enforced Multivariate Recurrent Neural Networks
Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks
Reducing Adversarially Robust Learning to Non-Robust PAC Learning
Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
Black-Box Optimization with Local Generative Surrogates
Efficient Generation of Structured Objects with Constrained Adversarial Networks
Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning
Recovery of sparse linear classifiers from mixture of responses
Efficient Distance Approximation for Structured High-Dimensional Distributions via Learning
A Single Recipe for Online Submodular Maximization with Adversarial or Stochastic Constraints
Learning Sparse Prototypes for Text Generation
Implicit Rank-Minimizing Autoencoder
Storage Efficient and Dynamic Flexible Runtime Channel Pruning via Deep Reinforcement Learning
Task-Oriented Feature Distillation
Entropic Causal Inference: Identifiability and Finite Sample Results
Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement
Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis
AdaTune: Adaptive Tensor Program Compilation Made Efficient
When Do Neural Networks Outperform Kernel Methods?
STEER : Simple Temporal Regularization For Neural ODE
A Variational Approach for Learning from Positive and Unlabeled Data
Efficient Clustering Based On A Unified View Of  K K K-means And Ratio-cut
Recurrent Switching Dynamical Systems Models for Multiple Interacting Neural Populations
Coresets via Bilevel Optimization for Continual Learning and Streaming
Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs
Understanding and Exploring the Network with Stochastic Architectures
All-or-nothing statistical and computational phase transitions in sparse spiked matrix estimation
Deep Evidential Regression
Analytical Probability Distributions and Exact Expectation-Maximization for Deep Generative Networks
Bayesian Pseudocoresets
See, Hear, Explore: Curiosity via Audio-Visual Association
Adversarial Training is a Form of Data-dependent Operator Norm Regularization
A Biologically Plausible Neural Network for Slow Feature Analysis
Learning Feature Sparse Principal Subspace
Online Adaptation for Consistent Mesh Reconstruction in the Wild
Online learning with dynamics: A minimax perspective
Learning to Select Best Forecast Tasks for Clinical Outcome Prediction
Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping
Adaptive Experimental Design with Temporal Interference: A Maximum Likelihood Approach
From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering
The Autoencoding Variational Autoencoder
A Fair Classifier Using Kernel Density Estimation
A Randomized Algorithm to Reduce the Support of Discrete Measures
Distributionally Robust Federated Averaging
Sharp uniform convergence bounds through empirical centralization
COBE: Contextualized Object Embeddings from Narrated Instructional Video
Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control
Finite Versus Infinite Neural Networks: an Empirical Study
Supermasks in Superposition
Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors
Almost Optimal Model-Free Reinforcement Learningvia Reference-Advantage Decomposition
Learning to Incentivize Other Learning Agents
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation
Distributionally Robust Local Non-parametric Conditional Estimation
Robust Multi-Object Matching via Iterative Reweighting of the Graph Connection Laplacian
Meta-Gradient Reinforcement Learning with an Objective Discovered Online
Learning Strategy-Aware Linear Classifiers
Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss
Calibrating Deep Neural Networks using Focal Loss
Optimizing Mode Connectivity via Neuron Alignment
Information Theoretic Regret Bounds for Online Nonlinear Control
A kernel test for quasi-independence
First Order Constrained Optimization in Policy Space
Learning Augmented Energy Minimization via Speed Scaling
Exploiting MMD and Sinkhorn Divergences for Fair and Transferable Representation Learning
Deep Rao-Blackwellised Particle Filters for Time Series Forecasting
Why are Adaptive Methods Good for Attention Models?
Neural Sparse Representation for Image Restoration
Boosting First-Order Methods by Shifting Objective: New Schemes with Faster Worst-Case Rates
Robust Sequence Submodular Maximization
Certified Monotonic Neural Networks
System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina
Efficient Algorithms for Device Placement of DNN Graph Operators
Active Invariant Causal Prediction: Experiment Selection through Stability
BOSS: Bayesian Optimization over String Spaces
Model Interpretability through the lens of Computational Complexity
Markovian Score Climbing: Variational Inference with KL(p||q)
Improved Analysis of Clipping Algorithms for Non-convex Optimization
Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection
StratLearner: Learning a Strategy for Misinformation Prevention in Social Networks
A Unified Switching System Perspective and Convergence Analysis of Q-Learning Algorithms
Kernel Alignment Risk Estimator: Risk Prediction from Training Data
Calibrating CNNs for Lifelong Learning
Online Convex Optimization Over Erdos-Renyi Random Networks
Robustness of Bayesian Neural Networks to Gradient-Based Attacks
Parametric Instance Classification for Unsupervised Visual Feature learning
Sparse Weight Activation Training
Collapsing Bandits and Their Application to Public Health Intervention
Neural Sparse Voxel Fields
A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding
The Discrete Gaussian for Differential Privacy
Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing
Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes
Learning efficient task-dependent representations with synaptic plasticity
A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions
Error Bounds of Imitating Policies and Environments
Disentangling Human Error from Ground Truth in Segmentation of Medical Images
Consequences of Misaligned AI
Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning
Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences
Hitting the High Notes: Subset Selection for Maximizing Expected Order Statistics
Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous GNNs
Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity
Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows
Few-shot Image Generation with Elastic Weight Consolidation
On the Expressiveness of Approximate Inference in Bayesian Neural Networks
Non-Crossing Quantile Regression for Distributional Reinforcement Learning
Dark Experience for General Continual Learning: a Strong, Simple Baseline
Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping
Neural encoding with visual attention
On the linearity of large non-linear models: when and why the tangent kernel is constant
PLLay: Efficient Topological Layer based on Persistent Landscapes
Decentralized Langevin Dynamics for Bayesian Learning
Shared Space Transfer Learning for analyzing multi-site fMRI data
The Diversified Ensemble Neural Network
Inductive Quantum Embedding
Variational Bayesian Unlearning
Batched Coarse Ranking in Multi-Armed Bandits
Understanding and Improving Fast Adversarial Training
Coded Sequential Matrix Multiplication For Straggler Mitigation
Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
Certifiably Adversarially Robust Detection of Out-of-Distribution Data
Domain Generalization via Entropy Regularization
Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels
Skeleton-bridged Point Completion: From Global Inference to Local Adjustment
Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding
Improved Guarantees for k-means++ and k-means++ Parallel
Sparse Spectrum Warped Input Measures for Nonstationary Kernel Learning
An Efficient Adversarial Attack for Tree Ensembles
Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
Online Bayesian Persuasion
Robust Pre-Training by Adversarial Contrastive Learning
Random Walk Graph Neural Networks
Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling
Fast and Accurate  k k k-means++ via Rejection Sampling
Variational Amodal Object Completion
When Counterpoint Meets Chinese Folk Melodies
Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces
Universal Domain Adaptation through Self Supervision
Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning​
Stochastic Normalization
Constrained episodic reinforcement learning in concave-convex and knapsack settings
On Learning Ising Models under Huber’s Contamination Model
Cross-validation Confidence Intervals for Test Error
DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
Bayesian Attention Modules
Robustness Analysis of Non-Convex Stochastic Gradient Descent using Biased Expectations
SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds
A meta-learning approach to (re)discover plasticity rules that carve a desired function into a neural network
Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough
Path Integral Based Convolution and Pooling for Graph Neural Networks
Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks
Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings
Conditioning and Processing: Techniques to Improve Information-Theoretic Generalization Bounds
Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
GAN Memory with No Forgetting
Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
Gaussian Gated Linear Networks
Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
Convex optimization based on global lower second-order models
Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition
Relative gradient optimization of the Jacobian term in unsupervised deep learning
Self-Supervised Visual Representation Learning from Hierarchical Grouping
Optimal Variance Control of the Score-Function Gradient Estimator for Importance-Weighted Bounds
Explicit Regularisation in Gaussian Noise Injections
Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning
Finite-Time Analysis for Double Q-learning
Learning to Detect Objects with a 1 Megapixel Event Camera
End-to-End Learning and Intervention in Games
Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms
Predictive coding in balanced neural networks with noise, chaos and delays
Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs
On the Equivalence between Online and Private Learnability beyond Binary Classification
AViD Dataset: Anonymized Videos from Diverse Countries
Probably Approximately Correct Constrained Learning
RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning
Decisions, Counterfactual Explanations and Strategic Behavior
Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample
A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization
Reservoir Computing meets Recurrent Kernels and Structured Transforms
Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection
Linear Dynamical Systems as a Core Computational Primitive
Ratio Trace Formulation of Wasserstein Discriminant Analysis
PAC-Bayes Analysis Beyond the Usual Bounds
Few-shot Visual Reasoning with Meta-Analogical Contrastive Learning
MPNet: Masked and Permuted Pre-training for Language Understanding
Reinforcement Learning with Feedback Graphs
Zap Q-Learning With Nonlinear Function Approximation
Lipschitz-Certifiable Training with a Tight Outer Bound
Fast Adaptive Non-Monotone Submodular Maximization Subject to a Knapsack Constraint
Conformal Symplectic and Relativistic Optimization
Bayes Consistency vs. H-Consistency: The Interplay between Surrogate Loss Functions and the Scoring Function Class
Inverting Gradients - How easy is it to break privacy in federated learning?
Dynamic allocation of limited memory resources in reinforcement learning
CryptoNAS: Private Inference on a ReLU Budget
A Stochastic Path Integral Differential EstimatoR Expectation Maximization Algorithm
CHIP: A Hawkes Process Model for Continuous-time Networks with Scalable and Consistent Estimation
SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection
Design Space for Graph Neural Networks
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
 Unbalanced Sobolev Descent 
Identifying Mislabeled Data using the Area Under the Margin Ranking
Combining Deep Reinforcement Learning and Search for Imperfect-Information Games
High-Throughput Synchronous Deep RL
Contrastive Learning with Adversarial Examples 
Mixed Hamiltonian Monte Carlo for Mixed Discrete and Continuous Variables
Adversarial Sparse Transformer for Time Series Forecasting
The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
CLEARER: Multi-Scale Neural Architecture Search for Image Restoration
Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights
Compositional Explanations of Neurons
Calibrated Reliable Regression using Maximum Mean Discrepancy
Directional convergence and alignment in deep learning
Functional Regularization for Representation Learning: A Unified Theoretical Perspective
Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits
Understanding Global Feature Contributions With Additive Importance Measures
Online Non-Convex Optimization with Imperfect Feedback
Co-Tuning for Transfer Learning
Multifaceted Uncertainty Estimation for Label-Efficient Deep Learning
Continuous Surface Embeddings
Succinct and Robust Multi-Agent Communication With Temporal Message Control
Big Bird: Transformers for Longer Sequences
Neural Execution Engines: Learning to Execute Subroutines
Random Reshuffling: Simple Analysis with Vast Improvements
Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
Statistical Optimal Transport posed as Learning Kernel Embedding
Dual-Resolution Correspondence Networks
Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization
f-Divergence Variational Inference
Unfolding recurrence by Green’s functions for optimized reservoir computing
The Dilemma of TriHard Loss and an Element-Weighted TriHard Loss for Person Re-Identification
Disentangling by Subspace Diffusion
Towards Neural Programming Interfaces
Discovering Symbolic Models from Deep Learning with Inductive Biases
Real World Games Look Like Spinning Tops
Cooperative Heterogeneous Deep Reinforcement Learning
Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization
ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool
Dense Correspondences between Human Bodies via Learning Transformation Synchronization on Graphs
Reasoning about Uncertainties in Discrete-Time Dynamical Systems using Polynomial Forms.
Applications of Common Entropy for Causal Inference
SGD with shuffling: optimal rates without component convexity and large epoch requirements
Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models
Neural Manifold Ordinary Differential Equations
CO-Optimal Transport
Continuous Meta-Learning without Tasks
A mathematical theory of cooperative communication
Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets
Learning Invariances in Neural Networks from Training Data
A Finite-Time Analysis of Two Time-Scale Actor-Critic Methods
Pruning Filter in Filter
Learning to Mutate with Hypergradient Guided Population
A convex optimization formulation for multivariate regression
Online Meta-Critic Learning for Off-Policy Actor-Critic Methods
The All-or-Nothing Phenomenon in Sparse Tensor PCA
Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis
ARMA Nets: Expanding Receptive Field for Dense Prediction
Diversity-Guided Multi-Objective Bayesian Optimization With Batch Evaluations
SOLOv2: Dynamic and Fast Instance Segmentation
Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization
Axioms for Learning from Pairwise Comparisons
Continuous Regularized Wasserstein Barycenters
Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
 
 

你可能感兴趣的:(论文阅读)

[论文阅读] 人工智能 + 软件工程 | 单会话方法论：一种以人类为中心的人工智能辅助软件开发协议张较瘦_ 前沿技术论文阅读人工智能软件工程
单一对话法（SCM）：AI辅助软件开发的“全局对话”新思路SingleConversationMethodology:AHuman-CenteredProtocolforAI-AssistedSoftwareDevelopmentarXiv:2507.12665SingleConversationMethodology:AHuman-CenteredProtocolforAI-AssistedSo
论文阅读：LLaVA1.5：Improved Baselines with Visual Instruction Tuning 微风❤水墨 LLM &AIGC &VLP LLM
论文：https://arxiv.org/abs/2310.03744代码：https://github.com/haotian-liu/LLaVA#train微调：https://github.com/haotian-liu/LLaVA/blob/main/docs/Finetune_Custom_Data.md模型论文时间VisionEncoderVLAdapterProjectionLaye
Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring 论文阅读钟屿论文阅读计算机视觉人工智能
用于动态场景去模糊的深度多尺度卷积神经网络摘要针对一般动态场景的非均匀盲去模糊是一个具有挑战性的计算机视觉问题，因为模糊不仅来源于多个物体运动，还来源于相机抖动和场景深度变化。为了去除这些复杂的运动模糊，传统的基于能量优化的方法依赖于简单的假设，例如模糊核是部分均匀或局部线性的。此外，最近的基于机器学习的方法也依赖于在这些假设下生成的合成模糊数据集。这使得传统的去模糊方法在模糊核难以近似或参数化的
[论文阅读]Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smal 0x211 论文阅读语言模型人工智能自然语言处理
中文译名：逐步蒸馏！以较少的训练数据和较小的模型规模超越较大的语言模型发布链接：http://arxiv.org/abs/2305.02301AcceptedtoFindingsofACL2023阅读原因：近期任务需要用到蒸馏操作，了解相关知识核心思想：改变视角。原来的视角：把LLMs视为噪声标签的来源。现在的视角：把LLMs视为能够推理的代理。方法好在哪？需要的数据量少，得到的结果好。文章的方法
【论文阅读】【IEEE TCYB 2023】Edge-Guided Recurrent Positioning Network forSalient Object Detection in Opt
引言任务：光学遥感图像中显著目标检测论文地址：Edge-GuidedRecurrentPositioningNetworkforSalientObjectDetectioninOpticalRemoteSensingImages|IEEEJournals&Magazine|IEEEXplore代码地址：前置知识一、摘要目前由于光学rsi中目标类型多样、目标尺度多样、目标方向众多以及背景杂乱，现有S
大模型服务的推理优化探索半吊子全栈工匠
【引】有的事情别人不问时我们明白，一旦要我们解释它我们就不明白了，而这正是我们必须留心思索的东西。于是，开启了一次又一次的论文阅读之旅。开发并部署大模型应用肯定要考虑它们的服务成本。然而，钱并不是唯一的考虑因素，如果不能解决模型性能方面的问题，即使有很大的预算，大模型服务仍会受到影响。本文尝试讨论将LLM推理服务更改为高吞吐量引擎的挑战与应对方法。1.大模型服务面临的挑战大模型的能力令人惊叹，但其
ER综述论文阅读-Emotion recognition in EEG signals using deep learning methods: A review 今天早睡了情绪识别Emotion Recognition 论文阅读深度学习人工智能
EmotionrecognitioninEEGsignalsusingdeeplearningmethods:AreviewQ1期刊，2023论文链接：https://d1wqtxts1xzle7.cloudfront.net/105887899/emotionreview-libre.pdf?1695460941=&response-content-disposition=inline%3B+f
【论文阅读】AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting quintus0505 LLM 论文阅读语言模型
AdaCtrl:TowardsAdaptiveandControllableReasoningviaDifficulty-AwareBudgeting3Method3.1长度触发标签作为控制接口（Length-TriggerTagsasControllingInterface）3.2冷启动微调（Cold-startfine-tuning）3.3难度感知的强化学习框架（Difficulty-awar
【论文阅读笔记】TimesURL: Self-supervised Contrastive Learning for Universal Time Series 少写代码少看论文多多睡觉 #论文阅读笔记论文阅读笔记
TimesURL:Self-supervisedContrastiveLearningforUniversalTimeSeriesRepresentationLearning摘要学习适用于多种下游任务的通用时间序列表示，并指出这在实际应用中具有挑战性但也是有价值的。最近，研究人员尝试借鉴自监督对比学习（SSCL）在计算机视觉（CV）和自然语言处理（NLP）中的成功经验，以解决时间序列表示的问题。
【论文阅读】Decoupled Knowledge Distillation Bosenya12 论文阅读
摘要：最先进的蒸馏方法主要基于从中间层蒸馏出深层特征，而logit蒸馏的重要性则被大大忽视了。为了提供研究logit蒸馏的新观点，我们将经典的KD损失重新表述为两部分，即目标类知识蒸馏（TCKD）和非目标类知识蒸馏（NCKD）。我们实证调查并证明了两部分的效果：TCKD传递了有关训练样本“困难”的知识，而NCKD是logit蒸馏起作用的突出原因。更重要的是，我们揭示了经典的KD损失是一个耦合公式，
【论文阅读】Transfer Learning for Automatic Modulation Recognition Using a Few Modulated Signal Samples
摘要：这封信提出了一种用于自动调制识别（AMR）的迁移学习模型，该模型仅具有少量调制信号样本。传输模型以音频信号UrbanSound8K作为源域进行训练，然后以一些调制信号样本为目标域进行微调。为了提高分类性能，信噪比（SNR）被用作一个功能来促进信号的分类。仿真结果表明，迁移模型在分类精度方面具有显著优势。这篇文章的核心内容是提出了一种基于迁移学习（TransferLearning）的自动调制识
【论文阅读】Meta-SE: A Meta-Learning Framework for Few-Shot Speech Enhancement Bosenya12 论文阅读
这篇文章介绍了一个名为Meta-SE的元学习框架，专门用于少样本（few-shot）语音增强问题。文章的核心目标是解决在实际应用中，由于训练样本有限而导致传统深度神经网络（DNN）模型性能受限的问题。Meta-SE通过元学习的方法，利用先验的元知识快速适应新的任务和噪声类型，即使只有少量训练样本也能表现出色。背景知识与研究动机语音增强技术旨在从带噪语音信号中恢复目标语音，提升语音质量和可懂度。深度
【论文阅读】SASLN：小样本条件下机械故障诊断的信号增强自学习网络
SASLN:SignalsAugmentedSelf-TaughtLearningNetworksforMechanicalFaultDiagnosisUnderSmallSampleCondition本文介绍了一种名为SASLN（SignalsAugmentedSelf-TaughtLearningNetworks）的方法，专门用于在小样本条件下对风力发电机（WT）的发电机轴承故障进行诊断。该方
【论文阅读】SSCL-AMC：一种基于动态增强和集成学习的自监督自动调制分类方法
SSCL-AMC:ASelf-supervisedAutomaticModulationClassificationMethodviaDynamicAugmentationandEnsembleLearning摘要：与传统的手工自动调制分类（AMC）方法相比，深度学习已经显示出有希望的结果，AMC作为信号检测和调制之间的中间步骤发挥着关键作用。然而，获取大规模标记数据仍然具有挑战性，因为数据质量和
[论文阅读] 人工智能 + 软件工程 | 当 LLM 写代码时，它的 “思考过程” 靠谱吗？—— 揭秘 CoT 质量的那些事儿张较瘦_ 前沿技术论文阅读人工智能软件工程
当LLM写代码时，它的“思考过程”靠谱吗？——揭秘CoT质量的那些事儿论文标题：AreTheyAllGood?EvaluatingtheQualityofCoTsinLLM-basedCodeGenerationarXiv:2507.06980[pdf,html,other]AreTheyAllGood?EvaluatingtheQualityofCoTsinLLM-basedCodeGenera
[论文阅读] 人工智能 + 软件工程 | 需求获取访谈中LLM生成跟进问题研究：来龙去脉与创新突破
需求获取访谈中LLM生成跟进问题研究：来龙去脉与创新突破论文标题：RequirementsElicitationFollow-UpQuestionGenerationarXiv:2507.02858RequirementsElicitationFollow-UpQuestionGenerationYuchenShen,AnmolSinghal,TravisBreauxComments:13page
Prompt相关论文阅读(02)--Auto-CoT(2024-11-25) zhilanguifang 论文 prompt engineering 论文阅读笔记
论文阅读笔记2024-11-24~2024-11-25Auto-CoT:AutomaticChainofThoughtPromptinginLargeLanguageModels(ICLR2023)碎碎念：复现代码和笔记保存到gitee仓库上海交通大学的学生在亚马逊实习的时候的成果ICLR2023摘要：LLM能够通过生成中间推理步骤执行复杂的推理。提供这些步骤用于提示演示叫做思维链提示CoT。Co
【论文阅读】Dynamic Few-Shot Visual Learning without Forgetting Bosenya12 论文阅读
系统概述如下：(a)一个基于卷积神经网络（ConvNet）的识别模型，该模型包含特征提取器和分类器；(b)一个少样本分类权重生成器。这两个组件都是在一组基础类别上训练的，我们为这些类别准备了大量训练数据。在测试阶段，权重生成器会接收少量新类别的训练数据以及基础类别的分类权重向量（分类器框内的绿色矩形），并为新类别生成相应的分类权重向量（分类器框内的蓝色矩形）。这样，卷积神经网络就能同时识别基础类别
【论文阅读】Few-Shot PPG Signal Generation via Guided Diffusion Models Bosenya12 论文阅读
从少量样本数据选择到后处理的整体框架。首先，扩散模型在N样本数据集和指导下的训练。接着，模型生成一个增强的数据集，并进一步优化以提高保真度。最后，这些合成数据与少量样本训练数据集结合，用于基准模型的训练和评估。数据分布从最初的红色变为保真度增强的蓝色，这表明模型与真实数据更加吻合，如简化后的数据分布示意图所示。这篇文章的核心内容是介绍了一种名为BG-Diff（Bi-GuidedDiffusion）
[论文阅读] 人工智能 | 读懂Meta-Fair：让LLM摆脱偏见的自动化测试新方法张较瘦_ 前沿技术论文阅读人工智能
读懂Meta-Fair：让LLM摆脱偏见的自动化测试新方法论文标题：Meta-Fair:AI-AssistedFairnessTestingofLargeLanguageModelsarXiv:2507.02533Meta-Fair:AI-AssistedFairnessTestingofLargeLanguageModelsMiguelRomero-Arjona,JoséA.Parejo,Jua
【LLM论文阅读】一只齐刘海的猫论文阅读
LLM论文阅读论文重点论文链接RopeRoFormer:EnhancedTransformerwithRotaryPositionEmbeddingRoPE论文阅读YarnUnderstandingYaRN:ExtendingContextWindowofLLMs论文YaRN笔记T5ExploringtheLimitsofTransferLearningwithaUnifiedText-to-Te
Segment Anything in High Quality之SAM-HQ论文阅读 qq_41627642 深度学习论文阅读论文阅读
摘要最近的SegmentAnythingModel（SAM）在扩展分割模型规模方面取得了重大突破，具备强大的零样本能力和灵活的提示机制。尽管SAM在训练时使用了11亿个掩码，其掩码预测质量在许多情况下仍不理想，尤其是对于结构复杂的目标。我们提出了HQ-SAM，使SAM能够精确地分割任意目标，同时保留其原有的可提示设计、高效性和零样本泛化能力。我们的设计充分复用并保留了SAM预训练的模型权重，仅引入
yolov算法详解_yolo 目标检测算法个人总结（yolov1） CHAO JIANG yolov算法详解
yolo目标检测算法个人总结目前yolo目标检测有两个版本，分别为v1和v2。因工作需要用yolo算法检测人物，所以这段时间重点看了这两篇论文，并实现了对应的tensorflow代码。这里记录下在论文阅读过程中的一些细节信息，留给自己，同时也希望各位能指出本人理解错误的地方，谢谢！一：yolov1关于yolov1算法的详解在网上已经非常多了，在这里我大概叙述下算法的流程，以及在开发过程中遇到的一些
《论文阅读》GPT-3是否会产生移情对话？一种新的情境示例选择方法和用于生成同理心对话的自动评估度量 ICCL 2022 365JHWZGo 情感对话论文阅读 gpt-3 共情回复上下文学习提示学习大模型
《论文阅读》GPT-3是否会产生移情对话？一种新的情境示例选择方法和用于生成同理心对话的自动评估度量ICCL2022前言贡献PromptIn-contextlearningSITSMEMOSITSM新的自动指标实验前言亲身阅读感受分享，细节画图解释，再也不用担心看不懂论文啦~无抄袭，无复制，纯手工敲击键盘~今天为大家带来的是《DoesGPT-3GenerateEmpatheticDialogues
[论文阅读] 人工智能 + 软件工程 | 揭秘ChatGPT在软件开发问题解决中的有效性：一项实证研究张较瘦_ 前沿技术论文阅读人工智能软件工程
揭秘ChatGPT在软件开发问题解决中的有效性：一项实证研究论文：WhatMakesChatGPTEffectiveforSoftwareIssueResolution?AnEmpiricalStudyofDeveloper-ChatGPTConversationsinGitHubarXiv:2506.22390WhatMakesChatGPTEffectiveforSoftwareIssueRe
[论文阅读] 人工智能 + 软件工程 | 代码注释不一致问题研究：从数据革新到端到端解决方案张较瘦_ 前沿技术论文阅读人工智能软件工程
代码注释不一致问题研究：从数据革新到端到端解决方案原文：CCISOLVER:End-to-EndDetectionandRepairofMethod-LevelCode-CommentInconsistencyarXiv:2506.20558CCISolver:End-to-EndDetectionandRepairofMethod-LevelCode-CommentInconsistencyRe
Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution论文阅读青铜锁00 #退化论文阅读深度学习论文阅读图像处理
LearningFullyConvolutionalNetworksforIterativeNon-blindDeconvolution1.研究目标与实际问题1.1研究目标1.2实际意义2.创新方法与模型设计2.1核心框架：迭代式梯度域处理2.1.1模型架构2.2关键技术实现2.2.1梯度域去噪网络2.2.2解卷积模块（核心公式实现）2.2.3损失函数设计2.2.4超参数端到端学习2.3与传统方法
KAIST数据集及使用草莓奶忻 SLAM基础 #SLAM数据集 ubuntu
文章目录KAIST复杂城市数据集KAIST数据集转换为rosbag1.将.gz.tar文件解压到其文件夹中2.克隆并构建此存储库3.使用路径和所需主题编辑配置文件4.为每种传感器类型创建一个rosbag文件5.将所有bag合并为一个参考KAIST复杂城市数据集KAIST-Urban-数据集-论文阅读数据集下载：ComplexUrbanDataset复杂城市数据集KAIST数据集转换为rosbag1
[论文阅读] 软件工程 | 需求工程中领域知识研究：系统映射与创新突破张较瘦_ 前沿技术论文阅读软件工程
需求工程中领域知识研究：系统映射与创新突破论文信息DomainKnowledgeinRequirementsEngineering:ASystematicMappingStudyarXiv:2506.20754DomainKnowledgeinRequirementsEngineering:ASystematicMappingStudyMarinaAraújo,JúliaAraújo,RomeuO
论文阅读：2025 arxiv Qwen3 Technical Report
https://arxiv.org/pdf/2505.09388https://www.doubao.com/chat/9918384373236738文章目录论文翻译Qwen3技术报告摘要1引言论文翻译Qwen3技术报告Qwen团队摘要在这项工作中，我们介绍了Qwen模型家族的最新版本Qwen3。Qwen3包含一系列大型语言模型（LLM），旨在提升性能、效率和多语言能力。Qwen3系列包括密集型
Java 并发包之线程池和原子计数 lijingyao8206 Java计数 ThreadPool 并发包 java线程池
对于大数据量关联的业务处理逻辑，比较直接的想法就是用JDK提供的并发包去解决多线程情况下的业务数据处理。线程池可以提供很好的管理线程的方式，并且可以提高线程利用率，并发包中的原子计数在多线程的情况下可以让我们避免去写一些同步代码。这里就先把jdk并发包中的线程池处理器ThreadPoolExecutor 以原子计数类AomicInteger 和倒数计时锁C
java编程思想抽象类和接口百合不是茶 java 抽象类接口
接口c++对接口和内部类只有简介的支持,但在java中有队这些类的直接支持 1 ,抽象类 : 如果一个类包含一个或多个抽象方法,该类必须限定为抽象类(否者编译器报错) 抽象方法 : 在方法中仅有声明而没有方法体 package com.wj.Interface;
[房地产与大数据]房地产数据挖掘系统 comsci 数据挖掘
随着一个关键核心技术的突破,我们已经是独立自主的开发某些先进模块,但是要完全实现,还需要一定的时间... 所以,除了代码工作以外,我们还需要关心一下非技术领域的事件..比如说房地产 &nb
数组队列总结沐刃青蛟数组队列
数组队列是一种大小可以改变，类型没有定死的类似数组的工具。不过与数组相比，它更具有灵活性。因为它不但不用担心越界问题，而且因为泛型（类似c++中模板的东西）的存在而支持各种类型。以下是数组队列的功能实现代码： import List.Student; public class
Oracle存储过程无法编译的解决方法 IT独行者 oracle 存储过程　
今天同事修改Oracle存储过程又导致2个过程无法被编译，流程规范上的东西，Dave 这里不多说，看看怎么解决问题。 1. 查看无效对象 XEZF@xezf(qs-xezf-db1)> select object_name,object_type,status from all_objects where status='IN
重装系统之后oracle恢复文强chu oracle
前几天正在使用电脑，没有暂停oracle的各种服务。突然win8.1系统奔溃，无法修复，开机时系统提示正在搜集错误信息，然后再开机，再提示的无限循环中。无耐我拿出系统u盘准备重装系统，没想到竟然无法从u盘引导成功。晚上到外面早了一家修电脑店，让人家给装了个系统，并且那哥们在我没反应过来的时候，直接把我的c盘给格式化了并且清理了注册表，再装系统。然后的结果就是我的oracl
python学习二（一些基础语法）小桔子 pthon 基础语法
紧接着把！昨天没看继续看django 官方教程，学了下python的基本语法与c类语言还是有些小差别： 1.ptyhon的源文件以UTF-8编码格式 2. / 除结果浮点型 // 除结果整形 % 除取余数 * 乘 ** 乘方 eg 5**2 结果是5的2次方25 _&
svn 常用命令 aichenglong SVN 版本回退
1 svn回退版本 1)在window中选择log,根据想要回退的内容,选择revert this version或revert chanages from this version 两者的区别: revert this version:表示回退到当前版本(该版本后的版本全部作废) revert chanages from this versio
某小公司面试归来 alafqq 面试
先填单子，还要写笔试题，我以时间为急，拒绝了它。。时间宝贵。老拿这些对付毕业生的东东来吓唬我。。面试官很刁难，问了几个问题，记录下； 1，包的范围。。。public,private,protect. --悲剧了 2，hashcode方法和equals方法的区别。谁覆盖谁.结果，他说我说反了。 3，最恶心的一道题，抽象类继承抽象类吗？（察，一般它都是被继承的啊） 4，stru
动态数组的存储速度比较集合框架百合不是茶集合框架
集合框架：自定义数据结构(增删改查等) package 数组; /** * 创建动态数组 * @author 百合 * */ public class ArrayDemo{ //定义一个数组来存放数据 String[] src = new String[0]; /** * 增加元素加入容器 * @param s要加入容器
用JS实现一个JS对象，对象里有两个属性一个方法 bijian1013 js对象
<html> <head> </head> <body> 用js代码实现一个js对象，对象里有两个属性，一个方法 </body> <script> var obj={a:'1234567',b:'bbbbbbbbbb',c:function(x){
探索JUnit4扩展：使用Rule bijian1013 java 单元测试 JUnit Rule
在上一篇文章中，讨论了使用Runner扩展JUnit4的方式，即直接修改Test Runner的实现(BlockJUnit4ClassRunner)。但这种方法显然不便于灵活地添加或删除扩展功能。下面将使用JUnit4.7才开始引入的扩展方式——Rule来实现相同的扩展功能。 1. Rule &n
[Gson一]非泛型POJO对象的反序列化 bit1129 POJO
当要将JSON数据串反序列化自身为非泛型的POJO时，使用Gson.fromJson(String, Class)方法。自身为非泛型的POJO的包括两种： 1. POJO对象不包含任何泛型的字段 2. POJO对象包含泛型字段，例如泛型集合或者泛型类 Data类 a.不是泛型类， b.Data中的集合List和Map都是泛型的 c.Data中不包含其它的POJO
【Kakfa五】Kafka Producer和Consumer基本使用 bit1129 kafka
0.Kafka服务器的配置一个Broker，一个Topic Topic中只有一个Partition（） 1. Producer： package kafka.examples.producers; import kafka.producer.KeyedMessage; import kafka.javaapi.producer.Producer; impor
lsyncd实时同步搭建指南——取代rsync+inotify ronin47
1. 几大实时同步工具比较 1.1 inotify + rsync 最近一直在寻求生产服务服务器上的同步替代方案，原先使用的是 inotify + rsync，但随着文件数量的增大到100W+，目录下的文件列表就达20M，在网络状况不佳或者限速的情况下，变更的文件可能10来个才几M，却因此要发送的文件列表就达20M，严重减低的带宽的使用效率以及同步效率；更为要紧的是，加入inotify
java-9. 判断整数序列是不是二元查找树的后序遍历结果 bylijinnan java
public class IsBinTreePostTraverse{ static boolean isBSTPostOrder(int[] a){ if(a==null){ return false; } /*1.只有一个结点时，肯定是查找树 *2.只有两个结点时，肯定是查找树。例如{5,6}对应的BST是 6 {6,5}对应的BST是
MySQL的sum函数返回的类型 bylijinnan java spring sql mysql jdbc
今天项目切换数据库时，出错访问数据库的代码大概是这样： String sql = "select sum(number) as sumNumberOfOneDay from tableName"; List<Map> rows = getJdbcTemplate().queryForList(sql); for (Map row : rows
java设计模式之单例模式 chicony java设计模式
在阎宏博士的《JAVA与模式》一书中开头是这样描述单例模式的：　　作为对象的创建模式，单例模式确保某一个类只有一个实例，而且自行实例化并向整个系统提供这个实例。这个类称为单例类。单例模式的结构　　单例模式的特点：单例类只能有一个实例。单例类必须自己创建自己的唯一实例。单例类必须给所有其他对象提供这一实例。　　饿汉式单例类 publ
javascript取当月最后一天 ctrain JavaScript
 <script language=javascript> var current = new Date(); var year = current.getYear(); var month = current.getMonth(); showMonthLastDay(year, mont
linux tune2fs命令详解 daizj linux tune2fs 查看系统文件块信息
一.简介： tune2fs是调整和查看ext2/ext3文件系统的文件系统参数，Windows下面如果出现意外断电死机情况，下次开机一般都会出现系统自检。Linux系统下面也有文件系统自检，而且是可以通过tune2fs命令，自行定义自检周期及方式。二.用法： Usage: tune2fs [-c max_mounts_count] [-e errors_behavior] [-g grou
做有中国特色的程序员 dcj3sjt126com 程序员
从出版业说起网络作品排到靠前的，都不会太难看，一般人不爱看某部作品也是因为不喜欢这个类型，而此人也不会全不喜欢这些网络作品。究其原因，是因为网络作品都是让人先白看的，看的好了才出了头。而纸质作品就不一定了，排行榜靠前的，有好作品，也有垃圾。许多大牛都是写了博客，后来出了书。这些书也都不次，可能有人让为不好，是因为技术书不像小说，小说在读故事，技术书是在学知识或温习知识，有
Android：TextView属性大全 dcj3sjt126com textview
android:autoLink 设置是否当文本为URL链接/email/电话号码/map时，文本显示为可点击的链接。可选值(none/web/email/phone/map/all) android:autoText 如果设置，将自动执行输入值的拼写纠正。此处无效果，在显示输入法并输
tomcat虚拟目录安装及其配置 eksliang tomcat配置说明 tomca部署web应用 tomcat虚拟目录安装
转载请出自出处：http://eksliang.iteye.com/blog/2097184 1.-------------------------------------------tomcat 目录结构 config：存放tomcat的配置文件 temp ：存放tomcat跑起来后存放临时文件用的 work ：当第一次访问应用中的jsp
浅谈：APP有哪些常被黑客利用的安全漏洞 gg163 APP
首先，说到APP的安全漏洞，身为程序猿的大家应该不陌生；如果抛开安卓自身开源的问题的话，其主要产生的原因就是开发过程中疏忽或者代码不严谨引起的。但这些责任也不能怪在程序猿头上，有时会因为BOSS时间催得紧等很多可观原因。由国内移动应用安全检测团队爱内测（ineice.com）的CTO给我们浅谈关于Android 系统的开源设计以及生态环境。 1. 应用反编译漏洞：APK 包非常容易被反编译成可读
C#根据网址生成静态页面 hvt Web .net C#asp.net hovertree
HoverTree开源项目中HoverTreeWeb.HVTPanel的Index.aspx文件是后台管理的首页。包含生成留言板首页，以及显示用户名，退出等功能。根据网址生成页面的方法： bool CreateHtmlFile(string url, string path) { //http://keleyi.com/a/bjae/3d10wfax.htm stri
SVG 教程（一）天梯梦 svg
SVG 简介 SVG 是使用 XML 来描述二维图形和绘图程序的语言。学习之前应具备的基础知识：继续学习之前，你应该对以下内容有基本的了解： HTML XML 基础如果希望首先学习这些内容，请在本站的首页选择相应的教程。什么是SVG？ SVG 指可伸缩矢量图形 (Scalable Vector Graphics) SVG 用来定义用于网络的基于矢量
一个简单的java栈 luyulong java 数据结构栈
public class MyStack { private long[] arr; private int top; public MyStack() { arr = new long[10]; top = -1; } public MyStack(int maxsize) { arr = new long[maxsize]; top
基础数据结构和算法八：Binary search sunwinner Algorithm Binary search
Binary search needs an ordered array so that it can use array indexing to dramatically reduce the number of compares required for each search, using the classic and venerable binary search algori
12个C语言面试题，涉及指针、进程、运算、结构体、函数、内存，看看你能做出几个！刘星宇 c 面试
12个C语言面试题，涉及指针、进程、运算、结构体、函数、内存，看看你能做出几个！ 1.gets()函数问：请找出下面代码里的问题： #include<stdio.h> int main(void) { char buff[10]; memset(buff,0,sizeof(buff));
ITeye 7月技术图书有奖试读获奖名单公布 ITeye管理员活动 ITeye 试读
ITeye携手人民邮电出版社图灵教育共同举办的7月技术图书有奖试读活动已圆满结束，非常感谢广大用户对本次活动的关注与参与。 7月试读活动回顾： http://webmaster.iteye.com/blog/2092746 本次技术图书试读活动的优秀奖获奖名单及相应作品如下（优秀文章有很多，但名额有限，没获奖并不代表不优秀）：《Java性能优化权威指南》