Location: Olin 305
When: March 14th at 1:30 p.m.
Title: The physics of inference, phase transitions, and community detection
Abstract: There is a deep analogy between Bayesian inference and statistical physics. When we fit a model to noisy data, we can think about the landscape of possible models, and look for phase transitions where the ground truth suddenly gets lost in this landscape — either because of “heat” or noise, or because of dynamics where the accurate states are hidden behind an “energy barrier” and thus take exponential time to find. I’ll use this framework to describe phase transitions in community detection in networks, where communities suddenly become hard or impossible to find. If time permits, I’ll discuss related spectral algorithms, and give a hint of similar phase transitions in other inference problems.
Zoom link: https://wse.zoom.us/j/94601022340