About the speaker:

Tin Nguyen (Nguyễn Danh Tín) is a PhD student at MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), working with Tamara Broderick on computational statistics. His research website is http://www.mit.edu/~tdn/.


Bayesian nonparametrics based on completely random measures (CRMs) offers a flexible modeling approach
when the number of clusters or latent components in a dataset is unknown. However, managing the infinite dimensionality of CRMs often leads to slow computation. Practical inference typically relies on either integrating out the infinite-dimensional parameter or using a finite approximation: a truncated finite approximation (TFA)
or an independent finite approximation (IFA). The atom weights of TFAs are constructed sequentially, while the atoms of IFAs are independent, which (1) make them well-suited for parallel and distributed computation and (2) facilitates more convenient inference schemes. While IFAs have been developed in certain special cases in the past, there has not yet been a general template for construction or a systematic comparison to TFAs. We show how to construct IFAs for approximating distributions in a large family of CRMs, encompassing all those typically used in practice. We quantify the approximation error between IFAs and the target nonparametric prior, and prove that, in the worst-case, TFAs provide more component-efficient approximations than IFAs. However, in experiments on image denoising and topic modeling tasks with real data, we find that the error of Bayesian approximation methods overwhelms any finite approximation error, and IFAs perform very similarly to TFAs.

Upcoming Speakers

Toward building a cost-effective and robust machine learning system

Cuong Nguyen

Florida International University

Title: Toward building a cost-effective and robust machine learning system

Date/Time: Friday, Oct 15 2021 - 10:00 am (GMT + 7)


Qiang Liu

The University of Texas at Austin

Title: TBD

Date/Time: Friday, Oct 22 2021 - 10:00 am (GMT + 7)