CS Peer Talk | GFlowNets: 探索概率推断及科学发现中的应用

第三十一期

报告人：张鼎怀, Mila

时间：10月11日（星期三）4:00pm

方式：静园五院204

报告信息

Title

GFlowNets: Exploration for Structured Probabilistic Inference

Abstract

This talk will introduce and discuss generative flow networks (GFlowNets), a learning framework for amortized sampling, from a sequential decision-making perspective. Different from reinforcement learning, which optimizes trajectory-level statistics, GFlowNet targets sampling proportional to the reward function over the terminal states in a Markov decision process. A family of algorithms could thus be derived (as in RL). Fruitful connection with previous probabilistic methods and control can be drawn. We would also talk about its wide application in science in domains such as causal discovery, and drug discovery, and combinatorial optimization.

Biography

Dinghuai Zhang is a PhD candidate at Mila, advised by Prof. Aaron Courville and Prof. Yoshua Bengio. His research focuses on the intersection of probabilistic inference and scientific discovery. From a methodology perspective, he studies how to incorporate structured exploration into inference problems such as sampling, leveraging the power of the generative flow network (GFlowNet) framework which revolves around active learning, Bayesian inference, black box optimization, and reinforcement learning. He develops methods for applications on different sorts of scientific discovery tasks, including sequence design, molecule synthesis, and combinatorial optimization. Dinghuai also has spent time in FAIR lab (Meta AI). Dinghuai obtained a bachelor’s degree in math from Peking University.

about CS Peer Talk

作为活动的发起人，我们来自北京大学图灵班科研活动委员会，主要由图灵班各年级同学组成。我们希望搭建一个CS同学交流的平台，促进同学间的交流合作，帮助同学练习展示，同时增进友谊。

目前在计划中的系列包括但不限于：

• 教程系列：学生讲者为主，介绍自己的研究领域

• 研究系列：学生讲者为主，介绍自己的研究成果

• 客座系列：邀请老师做主题报告

除非报告人特别要求，报告默认是非公开的，希望营造一个自由放松但又互相激励的交流氛围。

主讲嘉宾招募

如果你愿意和大家分享你的学术成果、经历经验，总结回顾、触发新思，欢迎报名自荐。

主讲人报名：发邮件至 cs_research_tc@163.com，写明想讲的题目、内容及时间。

北京大学图灵班科研活动委员会

—   版权声明  —

本微信公众号所有内容，由北京大学前沿计算研究中心微信自身创作、收集的文字、图片和音视频资料，版权属北京大学前沿计算研究中心微信所有；从公开渠道收集、整理及授权转载的文字、图片和音视频资料，版权属原作者。本公众号内容原作者如不愿意在本号刊登内容，请及时通知本号，予以删除。