Graduate Student / Postdoc Seminar

Multiple-Source Adaptation Problem

Speaker: Mehryar Mohri

Location: Warren Weaver Hall 1302

Date: Friday, April 4, 2014, 1 p.m.


The problem of adaptation is one of the most important problems in modern machine learning since, while massive data sets are commonly accessible, sample points often do not follow the same distribution.

I will discuss some solutions for the problem with remarkable properties and point out some interesting open algorithmic problems. Next I will further extend the theory and learning guarantees using the notion of Renyi divergence.

This is joint work with Y. Mansour and A. Rostami.