6月13日预告 | ICLR 2023 大模型主题Talk

点击蓝字

关注我们

AI TIME欢迎每一位AI爱好者的加入！

哔哩哔哩直播通道

扫码关注AI TIME哔哩哔哩官方账号预约直播

2023年6月13日19:30-20:30

讲者简介

王琦：

现任国防科技大学理学院数学系统计与运筹学讲师。2015.06-2017.12期间，他在国防科技大学攻读管理学硕士学位，师从黄金才教授和冯旸赫副教授，从事复杂性与随机优化研究。2019.06-2022.09期间，他在荷兰AMLab攻读计算机博士学位，师从Max Welling 教授和 Herke van Hoof博士，从事生成式人工智能与强化学习的研究。过去三年，他以第一作者在人工智能机器学习三大顶级会议ICML、NeurIPS 和 ICLR 累计发表了4篇论文，提出了一系列条件生成模型、元强化学习模型和统计推断算法，获得ICML2022 Travel Grant和NeurIPS2022 Scholar Award。

报告题目

Investigating the Inference Suboptimality of the Conditional Generative Model and How to Fix It

报告简介

The recent few years have witnessed the great potential of conditional generative models. Some works like GPT4 and Stable Diffusion exhibit incredible performance in Artificial Intelligence Generated Content (AIGC). This talk will focus on the fundamental issues of conditional generative models and take the neural process model (Garnelo et al., 2018) as an example to investigate the inference suboptimality of variational inference. To close the inference gap, I overview the available optimization objectives and construct the surrogate objective inspired by the variational expectation maximization. The resulting model, referred to as the Self-normalized Importance weighted Neural Process (SI-NP), can learn a more accurate functional prior and has an improvement guarantee concerning the target log-likelihood. Experimental results show the competitive performance of SI-NP over other objectives, guiding the design of inference algorithms for conditional generative models.

Reference: Qi Wang, Marco Federici, & Herke van Hoof, Bridge the Inference Gaps of Neural Processes via Expectation Maximization, ICLR2023.

往期精彩文章推荐

记得关注我们呀！每天都有新知识！

 关于AI TIME 

AI TIME源起于2019年，旨在发扬科学思辨精神，邀请各界人士对人工智能理论、算法和场景应用的本质问题进行探索，加强思想碰撞，链接全球AI学者、行业专家和爱好者，希望以辩论的形式，探讨人工智能和人类未来之间的矛盾，探索人工智能领域的未来。

迄今为止，AI TIME已经邀请了1100多位海内外讲者，举办了逾550场活动，超600万人次观看。

我知道你

在看

哦

~

点击 阅读原文 下载本篇论文！