2026年8月11日（周二）下午2:30，深圳河套学院荣幸地邀请到俄罗斯莫斯科高等经济大学计算机科学系的谢尔盖・萨姆索诺夫助理教授，在B301教室带来主题为“生成流网络的若干方法论”的学术报告分享。诚挚欢迎学院师生及对该领域感兴趣的产学研界同仁参与讲座。

Title

生成流网络的若干方法论

On Some Methodological Aspects of Generative Flow Networks

About the Speaker

谢尔盖・萨姆索诺夫 助理教授

Asst. Prof. Sergey Samsonov

谢尔盖・萨姆索诺夫现任俄罗斯莫斯科高等经济大学计算机科学系助理教授，同时担任随机算法与高维推断国际实验室负责人。他于2024年在高等经济大学取得数学博士学位。谢尔盖的主要研究方向包括随机逼近、采样方法以及强化学习。

谢尔盖・萨姆索诺夫已在本领域顶级期刊与会议上发表30余篇论文，包括COLT、ICML、NeurIPS、ICLR、AISTATS、《Journal of Machine Learning Research》（机器学习研究期刊）以及《Mathematics of Operations Research》（运筹学数学）等。

Sergey Samsonov is currently the head of the International Laboratory of Stochastic Algorithms and High-Dimensional Inference and an assistant professor at the Department of Computer Science, HSE University, Moscow, Russia. He obtained his PhD degree in mathematics from HSE University in 2024. Sergey's research interests are mainly related to stochastic approximation, sampling methods, and reinforcement learning.

Sergey Samsonov has authored more than 30 papers in leading journals and conferences in the field, including COLT, ICML, NeurIPS, ICLR, AISTATS, the Journal of Machine Learning Research, and Mathematics of Operations Research.

Abstract

GFlowNets（生成流网络）是一类生成模型，旨在学习从给定的概率分布中采样对象（该分布有时可能仅已知其未归一化的形式）。GFlowNets的核心思想是引入了两种随机策略：一种“前向策略”，用于逐步构建组合对象；另一种“后向策略”，用于逐步解构这些对象。在推理阶段，GFlowNets会在一个精心构建的有向无环图（DAG）环境中采样轨迹。

在本次报告中，将探讨GFlowNets近期的几种方法论应用。具体而言，将介绍一种放宽了“无环”假设的理论，并展示非无环的GFlowNets如何被应用于求解最短路径问题。此外，还将讨论该方法论如何应用于具有连续状态空间的采样方法。

GFlowNets are a family of generative models that learn to sample objects from a given probability distribution, potentially known only up to a normalizing constant. The key concept behind GFlowNets is the use of two stochastic policies: a forward policy, which incrementally constructs compositional objects, and a backward policy, which sequentially deconstructs them. During inference, GFlowNets sample trajectories in an appropriately constructed directed acyclic graph environment.

This talk discusses several recent methodological applications of the GFlowNets. It introduces a theory that relaxes the acyclicity assumption, and shows how non-acyclic GFlowNets can be applied for solving the shortest path problem. This talk will also discuss how the methodology applies to sampling methods with continuous state space.

Host

荆炳义 教授

Prof. Bingyi Jing

Date & Time

2026年8月11日（星期二）

下午2:30-4:00

Tuesday, August 11, 2026,

2:30PM – 4:00PM

Venue

深圳河套学院B301教室

（深圳市福田区福保街道红棉路6号，地图导航“深圳河套学院-南门”）

Room B401, Shenzhen Loop Area Institute

(6 Hongmian Rd, Fubao Sub-Street, Futian District, Shenzhen, navigate to "Shenzhen Loop Area Institute (South Gate)" on the map.)

Online link

扫码加入会议

Join the Meeting Online

腾讯会议号：948-1135-4043

Tencent Meeting：948-1135-4043