Mean Field Approximation in Bayesian Linear Regression

Mon Sep 20, 2021 4:00 p.m.—5:00 p.m.
Sumit

This event has passed.

Sumit

Speaker

Sumit Mukherjee, Department of Statistics at Columbia University

In this talk we study the problem of Bayesian linear regression, where the coefficients have an iid prior. We show that the log normalizing constant of the posterior is “well approximated” by the mean field prediction formula, for a wide class of design matrices. Our techniques allow the design matrix to be deterministic/random with dependent entries. If the data is generated from a “true” linear model, we compute asymptotics of the log normalizing constant, in terms of an optimizing problem over the space of measures. If this optimization has a unique solution, we derive a Law of Large Numbers for the posterior.
Sumit Mukherjee’s website

 This talk is based on joint work with Subhabrata Sen

You are invited to a scheduled Zoom meeting. Zoom is Yale’s audio and visual conferencing platform.

Topic: Yale S&DS Department Seminar

Time: 4:00pm - 5:00pm

The Zoom link

    Password: 24

    Or Telephone：203-432-9666 (2-ZOOM if on-campus) or 646 568 7788

    Meeting ID: 991 6970 0816

    International numbers available: https://yale.zoom.us/u/acBOaD1ic6

For H.323 and SIP information for video conferencing units