Mathematical Optimization in The Era of AI

Abstract

This lecture aims to present several mathematical optimization problems/algorithms arising from LLM training, tuning and inference. In particular, the speaker will describe how classic optimization models/theories can be applied to accelerate and improve the algorithms that are popularly used in LLMs. On the other hand, the speaker will show breakthroughs in classical Optimization (LP and SDP) Solver developments aided by AI-related techniques such as online-learning, first-order and ADMM methods, the low-rank SDP theorem, and their implementations on GPU.

About the Speaker

Prof. Yinyu YE is currently the Visiting Professor of Shanghai Jiao Tong University and The Hong Kong University of Science and Technology. He was K.T. Li Professor of Engineering at Department of Management Science and Engineering and Institute of Computational and Mathematical Engineering, Stanford University. 

As a leading expert in optimization, he has received numerous academic awards including: the 2006 Farkas Prize (Inaugural Recipient) for fundamental contributions to optimization, the 2009 John von Neumann Theory Prize for fundamental sustained contributions to theory in Operations Research and the Management Sciences, the inaugural 2012 ISMP Tseng Lectureship Prize for outstanding contribution to continuous optimization (every three years), the 2014 Society of Industrial and Applied Mathematics Optimization Prize awarded (every three years), the 2025 Constantin Caratheodory Prize of the Global Optimization Congress.

For Attendees' Attention

Seating is on a first come, first served basis.