Graduate Student / Postdoc Seminar

Learning to Rank

Speaker: Mehryar Mohri

Location: Warren Weaver Hall 1302

Date: Friday, April 9, 2010, 1 p.m.


Ranking is a critical task in a variety of modern large-scale applications, including the design of search engines and information extraction systems. This talk presents an introduction to the learning problem of ranking. It also describes some recent algorithms, including a novel preference-based technique based on the familiar QuickSort, which benefits from remarkable theoretical guarantees.

Part of this talk is joint work with Nir Ailon, Corinna Cortes, and Ashish Rastogi.