Event Date
Speaker: Qijia Jiang, Post-Doctoral Researcher, Lawrence Berkeley National Lab
Title: "Optimization, Sampling Dynamics and Diffusion"
Abstract: Optimization plays an important role across data science, from guiding decision making under uncertainty, to modeling equilibrium in game dynamics. In this talk, I will begin by describing a line of work studying information-theoretic complexity in optimization under novel oracle models, aiming to provide a fundamental understanding of the problem hardness in these settings. In the second half of the talk, I will describe ways to conceptualize designing optimization dynamics in infinite-dimensional metric spaces, leading to interesting (geometry-aware) sampling algorithms and (controlled) diffusion processes. Time permitting, I will end by drawing connections of these ideas to other areas of research in data science and outline exciting directions for both methodology developments and applications.
Seminar Date/Time: Monday January 29, 2024 at 11:00am
Location: MSB 1147