Workshop on Probability, Inference, and Algorithms

Additional website

http://willperkins.org/inference2022.html

Schedule

2:30pm - 3:00pm: Discussion, welcome
3:00pm - 3:40pm: Vishesh Jain   "Entropic independence"
3:45pm - 4:25pm: Cynthia Rush "On the Robustness to Misspecification of α-Posteriors and Their Variational Approximations"
4:30pm - 5:10pm: Tyler Helmuth "Phase Transitions for Random Forests"

Abstracts

Vishesh Jain (Stanford): Entropic independence

Abstract: I will introduce entropic independence, which is an entropic analog of the recently established notion of spectral independence, and discuss how it may be used to obtain asymptotically sharp results on the mixing times of certain `local' random walks such as the Glauber dynamics for the Ising model or the hard-core model in the tree-uniquess regime.

Based on joint works with Nima Anari, Frederic Koehler, Huy Tuan Pham, and Thuy-Duong Vuong.

Cynthia Rush (Columbia): On the Robustness to Misspecification of α-Posteriors and Their Variational Approximations

Abstract: Variational inference (VI) is a machine learning technique that approximates difficult-to-compute probability densities by using optimization. While VI has been used in numerous applications, it is particularly useful in Bayesian statistics where one wishes to perform statistical inference about unknown parameters through calculations on a posterior density. In this talk, I will review the core concepts of VI and introduce some new ideas about VI and robustness to model misspecification. In particular, we will study α-posteriors, which distort standard posterior inference by downweighting the likelihood, and their variational approximations. We will see that such distortions, if tuned appropriately, can outperform standard posterior inference when there is potential parametric model misspecification. This is joint work with Marco Avella Medina, José Luis Montiel Olea, and Amilcar Velez (https://arxiv.org/abs/2104.08324).

Tyler Helmuth (Durham): Phase Transitions for Random Forests