#  Statistics Colloquium: Subhabrata Sen (Harvard University) 

 



####  calendar\_today Date and Time 

 **October 18, 2021** 

 12:00PM - 01:00PM EDT 

####  pin\_drop Location 

 **Please contact emilie_campanelli@fas.harvard.edu for more information**  



 

 



 

###    ![Headshot of Subhabrata Sen](/sites/g/files/omnuum10116/files/styles/hwp_1_1__360x360_scale/public/statistics-2/files/sen_headshot.jpg?itok=BP32j-I6) 

 

Title:

 High-dimensional Bayesian Regression: Asymptotics via the Naive Mean-field Approximation

###  Abstract:

 Variational approximations provide an attractive computational alternative to MCMC-based strategies for approximating the posterior distribution in Bayesian inference. Despite their popularity in applications, supporting theoretical guarantees are limited, particularly in high-dimensional settings. We study bayesian inference in the context of a linear model with product priors, and derive sufficient conditions for the correctness (to leading order) of the naive mean-field approximation. To this end, we utilize recent advances in the theory of *non-linear large deviations* (Chatterjee and Dembo 2014). Next, we analyze the naive mean-field variational problem, and precisely characterize the asymptotic properties of the posterior distribution in this setting.

 This is based on joint work with Sumit Mukherjee (Columbia University).



 

 



 

 See also:- [ Colloquia ](/event-type/colloquia)
 
 

 Share on:- [     Facebook ](#)
- [     Twitter ](#)
- [     Linkedin ](#)
 


 Save: [ Add to calendar calendar\_today ](https://statistics.fas.harvard.edu/node/1413663/event-feed.ics)  Copy link link