Linh Huynh: Spin-Glass-Based Active Inference for Transformers

Spin glasses is a subfield of high-dimensional probability and statistical physics that studies large networks with random interactions and conflicting combinatorial energy optimization constraints. Originally developed to understand disordered magnets, spin glass models have since found powerful applications in Artificial Intelligence/Machine Learning, and are increasingly being connected to problems in eco-evolutionary biology. Active inference is a partially observable Markov Decision Process framework where an agent uses Bayesian inference to perceive its surrounding environment and then makes decisions by minimizing the associated free energy. In this talk, I will discuss my integration of these two methods to design a mathematical framework for transformers in Large Language Models, which contributes to a broader goal of studying adaptive dynamics on high-dimensional optimization landscapes.

Speaker: Linh Huynh is a postdoc at the Department of Mathematics at Dartmouth College. Her research interests are applied probability & stochastic processes and their intersections with optimization under uncertainty, statistical inference, and mathematical biology (stochastic population dynamics).