报告人： 马易安（University of California, San Diego）
时间：2025-12-25 14:00-15:00
地点：智华楼四元厅-225
Abstract:
In the first part of the talk, I will discuss an interesting phenomenon in multi-agent learning, that the mixed Nash equilibria are uniformly stable if and only if they are collectively rational. This justifies the effusive use of multi-agent learning systems and resolves the 'as if' rationality problem in classical economics. If partial knowledge (about utility or algorithm) can be obtained about the opponents, then the agent can steer towards their favorable Stackelberg equilibria, surpassing Nash outcomes.
In the second part of the talk, I will discuss some recent progress on quantifying the epistemic uncertainty of large language models (LLMs). I will draw inspiration from existing works that quantifies uncertainty in forecasting problems and apply the intuition to the generative models.
About the Speaker:
Yian Ma is an assistant professor at the Halıcıoğlu Data Science Institute, UC San Diego. Prior to UCSD, he spent a year as a visiting faculty at Google Research. Before that, he was a post-doctoral fellow at UC Berkeley, hosted by Mike Jordan. Yian completed his Ph.D. at University of Washington. His current research primarily revolves around scalable inference methods for credible machine learning, with application to time series data and sequential decision making tasks. He has received the Facebook research award, the Stein fellowship, and the best paper awards at the Neurips and ICML workshops.
Your participation is warmly welcomed!
欢迎扫码关注北大统计科学中心公众号，了解更多讲座信息!
