同步公众号(arXiv每日论文速递),回复'search 关键词'查询相关最新论文。(* ̄rǒ ̄)
cs.LG 方向,今日共计60篇
[cs.LG]:
【1】 NUQSGD: Improved Communication Efficiency for Data-parallel SGD via Nonuniform Quantization
标题:NUQSGD:通过非均匀量化提高数据并行SGD的通信效率
作者: Ali Ramezani-Kebrya, Daniel M. Roy
链接:https://arxiv.org/abs/1908.06077
【2】 Convex geometry of the Coding problem for error constrained Dictionary Learning
标题:错误约束字典学习编码问题的凸几何
作者: Mohammed Rayyan Sheriff, Debasish Chatterjee
链接:https://arxiv.org/abs/1908.06065
【3】 Performing Deep Recurrent Double Q-Learning for Atari Games
标题:为Atari游戏执行深度循环双Q-学习
作者: Felipe Moreno-Vera
备注:Accepted paper on LatinxinAI Workshop co-located with the International Conference on Machine Learning (ICML) 2019
链接:https://arxiv.org/abs/1908.06040
【4】 ScarletNAS: Bridging the Gap Between Scalability and Fairness in Neural Architecture Search
标题:ScarletNAS:在神经架构搜索中弥合可伸缩性和公平性之间的鸿沟
作者: Xiangxiang Chu, Ruijun Xu
链接:https://arxiv.org/abs/1908.06022
【5】 Double-Coupling Learning for Multi-Task Data Stream Classification
标题:多任务数据流分类的双耦合学习
作者: Yingzhong Shi, Shitong Wang
备注:This work has been accepted conditionally by IEEE Computational Intelligence Magazine in July 2019
链接:https://arxiv.org/abs/1908.06021
【6】 Model-based Lookahead Reinforcement Learning
标题:基于模型的前瞻强化学习
作者: Zhang-Wei Hong, Jan Peters
链接:https://arxiv.org/abs/1908.06012
【7】 Variational Fusion for Multimodal Sentiment Analysis
标题:多模态情感分析的变分融合
作者: Navonil Majumder, Alexander Gelbukh
链接:https://arxiv.org/abs/1908.06008
【8】 Iterative Neural Networks with Bounded Weights
标题:有界权重的迭代神经网络
作者: Tomasz Piotrowski, Krzysztof Rykaczewski
链接:https://arxiv.org/abs/1908.05982
【9】 The Partial Response Network
标题:局部响应网络
作者: Paulo J. G. Lisboa, Ivan Olier
链接:https://arxiv.org/abs/1908.05978
【10】 AI Predicts Independent Construction Safety Outcomes from Universal Attributes
标题:人工智能根据通用属性预测独立的施工安全结果
作者: Henrietta Baker, Antoine J.-P. Tixier
链接:https://arxiv.org/abs/1908.05972
【11】 N2D:(Not Too) Deep clustering via clustering the local manifold of an autoencoded embedding
标题:N2D:(不太)通过对自动编码嵌入的局部流形进行聚类来进行深度聚类
作者: Ryan McConville, Ian Craddock
链接:https://arxiv.org/abs/1908.05968
【12】 Federated Learning with Additional Mechanisms on Clients to Reduce Communication Costs
标题:具有额外客户端机制的联合学习,以降低通信成本
作者: Xin Yao, Lifeng Sun
备注:This is a combination version of our papers in VCIP 2018 and ICIP 2019
链接:https://arxiv.org/abs/1908.05891
【13】 Generating Random Parameters in Feedforward Neural Networks with Random Hidden Nodes: Drawbacks of the Standard Method and How to Improve It
标题:在具有随机隐节点的前馈神经网络中产生随机参数:标准方法的缺陷及其改进
作者: Grzegorz Dudek
链接:https://arxiv.org/abs/1908.05864
【14】 A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems
标题:动态地下流动问题中数据同化的基于深度学习的代理模型
作者: Meng Tang, Louis J. Durlofsky
链接:https://arxiv.org/abs/1908.05823
【15】 Linear Stochastic Bandits Under Safety Constraints
标题:安全约束下的线性随机Bandts
作者: Sanae Amani, Christos Thrampoulidis
链接:https://arxiv.org/abs/1908.05814
【16】 Multitask and Transfer Learning for Autotuning Exascale Applications
标题:用于自动调整Exascale应用程序的多任务和转移学习
作者: Wissam M. Sid-Lakhdar, James W. Demmel
链接:https://arxiv.org/abs/1908.05792
【17】 M-BERT: Injecting Multimodal Information in the BERT Structure
标题:M-BERT:在BERT结构中注入多模态信息
作者: Wasifur Rahman, Mohammed Ehsan Hoque
链接:https://arxiv.org/abs/1908.05787
【18】 Examining the Use of Temporal-Difference Incremental Delta-Bar-Delta for Real-World Predictive Knowledge Architectures
标题:检验时间-差异增量-条形-增量用于真实世界预测性知识体系结构的使用
作者: Johannes Günther, Patrick M. Pilarski
链接:https://arxiv.org/abs/1908.05751
【19】 Heuristic Dynamic Programming for Adaptive Virtual Synchronous Generators
标题:自适应虚拟同步发电机的启发式动态规划
作者: Sepehr Saadatmand, Donald C. Wunsch
备注:NAPS 2019 Conference. arXiv admin note: substantial text overlap with arXiv:1908.05191; text overlap with arXiv:1908.05199
链接:https://arxiv.org/abs/1908.05744
【20】 Trustable and Automated Machine Learning Running with Blockchain and Its Applications
标题:块链运行的可信自动机器学习及其应用
作者: Tao Wang, Taiping He
备注:10 pages, KDD 2019 AutoML workshop. arXiv admin note: text overlap with arXiv:1903.08801
链接:https://arxiv.org/abs/1908.05725
【21】 Convergence Behaviour of Some Gradient-Based Methods on Bilinear Games
标题:双线性对策上几种基于梯度的方法的收敛性
作者: Guojun Zhang, Yaoliang Yu
链接:https://arxiv.org/abs/1908.05699
【22】 Effect of Activation Functions on the Training of Overparametrized Neural Nets
标题:激活函数对过参数化神经网络训练的影响
作者: Abhishek Panigrahi, Navin Goyal
链接:https://arxiv.org/abs/1908.05660
【23】 An Exploratory Analysis of the Latent Structure of Process Data via Action Sequence Autoencoder
标题:通过动作序列自动编码器对过程数据潜在结构的探索性分析
作者: Xueying Tang, Zhiliang Ying
链接:https://arxiv.org/abs/1908.06075
【24】 Adversarial point perturbations on 3D objects
标题:3D物体上的对抗性点扰动
作者: Daniel Liu, Hao Su
链接:https://arxiv.org/abs/1908.06062
【25】 Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification
标题:恢复和识别:交叉分辨人员重新识别的生成性对偶模型
作者: Yu-Jhe Li, Yu-Chiang Frank Wang
备注:Accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.06052
【26】 AutoER: Automated Entity Resolution using Generative Modelling
标题:AutoER:使用生成建模的自动实体解析
作者: Renzhi Wu, Saravanan Thirumuruganathan
链接:https://arxiv.org/abs/1908.06049
【27】 Few-shot Text Classification with Distributional Signatures
标题:具有分布特征的少镜头文本分类
作者: Yujia Bao, Regina Barzilay
链接:https://arxiv.org/abs/1908.06039
【28】 Needles in Haystacks: On Classifying Tiny Objects in Large Images
标题:干草堆中的针:大图像中微小物体的分类
作者: Nick Pawlowski, Michal Drozdzal
链接:https://arxiv.org/abs/1908.06037
【29】 Towards automated symptoms assessment in mental health
标题:走向心理健康中的症状自动评估
作者: Maxim Osipov
链接:https://arxiv.org/abs/1908.06013
【30】 Safe global optimization of expensive noisy black-box functions in the -Lipschitz framework
标题:-Lipschitz框架中昂贵噪声黑盒函数的安全全局优化
作者: Yaroslav D. Sergeyev (1 and 2), Italy)
链接:https://arxiv.org/abs/1908.06010
【31】 Bidirectional Context-Aware Hierarchical Attention Network for Document Understanding
标题:用于文档理解的双向上下文感知分层注意网络
作者: Jean-Baptiste Remy, Michalis Vazirgiannis
链接:https://arxiv.org/abs/1908.06006
【32】 Higher-Order Visualization of Causal Structures in Dynamics Graphs
标题:动力学图中因果结构的高阶可视化
作者: Vincenzo Perri, Ingo Scholtes
链接:https://arxiv.org/abs/1908.05976
【33】 Multi-Domain Adaptation in Brain MRI through Paired Consistency and Adversarial Learning
标题:通过成对一致性和对抗性学习实现脑MRI中的多域适应
作者: Mauricio Orbes-Arteaga, M. Jorge Cardos
备注:DART MICCAI whorshop 2019
链接:https://arxiv.org/abs/1908.05959
【34】 FSGAN: Subject Agnostic Face Swapping and Reenactment
标题:FSGAN:主体不可知性面孔交换和重现
作者: Yuval Nirkin, Tal Hassner
备注:2019 IEEE/CVF International Conference on Computer Vision (ICCV)
链接:https://arxiv.org/abs/1908.05932
【35】 Attending to Future Tokens For Bidirectional Sequence Generation
标题:关注双向序列生成的未来令牌
作者: Carolin Lawrence, Mathias Niepert
备注:Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019, Hong Kong, China
链接:https://arxiv.org/abs/1908.05915
【36】 MFA is a Waste of Time! Understanding Negative Connotation Towards MFA Applications via User Generated Content
标题:MFA是浪费时间!通过用户生成的内容了解MFA应用的负面内涵
作者: Sanchari Das, L. Jean Camp
备注:Proceedings of the Thirteenth International Symposium on Human Aspects of Information Security & Assurance (HAISA 2019)
链接:https://arxiv.org/abs/1908.05902
【37】 Distilling On-Device Intelligence at the Network Edge
标题:在网络边缘提取设备上智能
作者: Jihong Park, Mehdi Bennis
链接:https://arxiv.org/abs/1908.05895
【38】 Regression on imperfect class labels derived by unsupervised clustering
标题:基于无监督聚类的不完美类标签回归
作者: Rasmus Froberg Brøndum, Martin Bøgsted
链接:https://arxiv.org/abs/1908.05885
【39】 Incorporating human and learned domain knowledge into training deep neural networks: A differentiable dose volume histogram and adversarial inspired framework for generating Pareto optimal dose distributions in radiation therapy
标题:将人类和学习的领域知识结合到训练深度神经网络中:可微分的剂量体积直方图和对抗性启发的框架,用于生成放射治疗中的Pareto最优剂量分布
作者: Dan Nguyen, Steve Jiang
链接:https://arxiv.org/abs/1908.05874
【40】 Differentiable Learning-to-Group Channels viaGroupable Convolutional Neural Networks
标题:通过可分组卷积神经网络的可区分的学习到组的通道
作者: Zhaoyang Zhang, Ping Luo
备注:accepted by ICCV 2019
链接:https://arxiv.org/abs/1908.05867
【41】 Sub-Spectrogram Segmentation for Environmental Sound Classification via Convolutional Recurrent Neural Network and Score Level Fusion
标题:基于卷积递归神经网络和分数级融合的环境声分类的子谱图分割
作者: Tianhao Qiao, Shugong Xu
备注:accepted in the 2019 IEEE International Workshop on Signal Processing Systems (SiPS2019)
链接:https://arxiv.org/abs/1908.05863
【42】 Recurrent U-net: Deep learning to predict daily summertime ozone in the United States
标题:经常性U-NET:深入学习预测美国每日夏季臭氧
作者: Tai-Long He, John R. Worden
链接:https://arxiv.org/abs/1908.05841
【43】 Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss
标题:Tag2Pix:使用带有SECAT和更改损失的文本标签进行线条艺术着色
作者: Hyunsu Kim, Sungjoo Yoo
备注:Accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.05840
【44】 A Cooperative Autoencoder for Population-BasedRegularization of CNN Image Registration
标题:一种基于群体的协同自动编码器CNN图像配准规则
作者: Riddhish Bhalodia, Ross T. Whitaker
备注:To appear in MICCAI 2019
链接:https://arxiv.org/abs/1908.05825
【45】 Kernel Sketching yields Kernel JL
标题:内核草图生成内核JL
作者: Samory Kpotufe, Bharath K. Sriperumbudur
链接:https://arxiv.org/abs/1908.05818
【46】 Using Wasserstein-2 regularization to ensure fair decisions with Neural-Network classifiers
标题:使用Wasserstein-2正则化确保神经网络分类器的公平决策
作者: Laurent Risser, Jean-Michel Loubes
链接:https://arxiv.org/abs/1908.05783
【47】 Experimental performance of graph neural networks on random instances of max-cut
标题:图神经网络在最大割随机实例上的实验性能
作者: Weichi Yao, Soledad Villar
链接:https://arxiv.org/abs/1908.05767
【48】 Learning Sub-Sampling and Signal Recovery with Applications in Ultrasound Imaging
标题:学习子采样和信号恢复在超声成像中的应用
作者: Iris A.M. Huijben, Ruud J.G. van Sloun
链接:https://arxiv.org/abs/1908.05764
【49】 On the Robustness of Projection Neural Networks For Efficient Text Representation: An Empirical Study
标题:投影神经网络用于高效文本表示的稳健性:一项实证研究
作者: Chinnadhurai Sankar, Zornitsa Kozareva
链接:https://arxiv.org/abs/1908.05763
【50】 Entity-aware ELMo: Learning Contextual Entity Representation for Entity Disambiguation
标题:实体感知ELMO:学习上下文实体表示以消除实体歧义
作者: Hamed Shahbazi, Prasad Tadepalli
链接:https://arxiv.org/abs/1908.05762
【51】 Similarity-based Android Malware Detection Using Hamming Distance of Static Binary Features
标题:基于静态二值特征汉明距离的Android恶意软件检测
作者: Rahim Taheri, Mauro Conti
备注:18 pages, 8 figures, 8 tables, FGCS Elsevier journal
链接:https://arxiv.org/abs/1908.05759
【52】 DeepHuMS: Deep Human Motion Signature for 3D Skeletal Sequences
标题:DeepHuMS:3D骨骼序列的深层人体运动特征
作者: Neeraj Battan, Avinash Sharma
链接:https://arxiv.org/abs/1908.05750
【53】 Skin Lesion Segmentation and Classification for ISIC 2018 by Combining Deep CNN and Handcrafted Features
标题:结合深度CNN和手工特征的ISIC 2018皮肤病变分割和分类
作者: Redha Ali, Temesguen Messay Kebede
链接:https://arxiv.org/abs/1908.05730
【54】 Video Compression With Rate-Distortion Autoencoders
标题:利用率失真自动编码器进行视频压缩
作者: Amirhossein Habibian, Taco S. Cohen
备注:Accepted to ICCV 2019
链接:https://arxiv.org/abs/1908.05717
【55】 Automated classification of plasma regions using 3D particle energy distribution
标题:使用3D粒子能量分布的等离子体区域的自动分类
作者: Vyacheslav Olshevsky, Stefano Markidis
链接:https://arxiv.org/abs/1908.05715
【56】 Transformer-based Automatic Post-Editing with a Context-Aware Encoding Approach for Multi-Source Inputs
标题:基于变压器的多源输入的上下文感知编码方法的自动后期编辑
作者: WonKee Lee, Jong-Hyeok Lee
链接:https://arxiv.org/abs/1908.05679
【57】 Bypass Enhancement RGB Stream Model for Pedestrian Action Recognition of Autonomous Vehicles
标题:用于自主车辆行人行为识别的旁路增强RGB流模型
作者: Dong Cao, Lisha Xu
备注:Submitted to ACPR 2019 - Workshop on Computer Vision for Modern Vehicles
链接:https://arxiv.org/abs/1908.05674
【58】 Towards Making the Most of BERT in Neural Machine Translation
标题:在神经机器翻译中最大限度地利用BERT
作者: Jiacheng Yang, Lei Li
链接:https://arxiv.org/abs/1908.05672
【59】 Resolvable Designs for Speeding up Distributed Computing
标题:用于加速分布式计算的可解析设计
作者: Konstantinos Konstantinidis, Aditya Ramamoorthy
备注:14 pages, 3 figures, full paper for IEEE TON submission. arXiv admin note: substantial text overlap with arXiv:1802.03049, arXiv:1901.07418
链接:https://arxiv.org/abs/1908.05666
【60】 Automatic detection and diagnosis of sacroiliitis in CT scans as incidental findings
标题:CT扫描中作为偶然发现的骶髂关节炎的自动检测和诊断
作者: Yigal Shenkman, Iris Eshed
链接:https://arxiv.org/abs/1908.05663
翻译:腾讯翻译君