Statistical Consistency and Regret Bounds for Ranking

125 views · Published 12 August 2016 · 36:42 · Indexed 6 November 2026

Channel: Microsoft Research · 2016 · Science & Technology

Watch on YouTube

Ranking problems arise in an increasing number of applications, including for example information retrieval, recommendation systems, computational biology, drug discovery, and a variety of industrial prioritization tasks.   In recent years, there has been much interest in developing machine learning algorithms for ranking problems, and in understanding the statistical properties of such algorithms. This talk will start with a brief overview of some recent results on the statistical consistency properties of ranking algorithms. The second part of the talk will then present some new results on regret bounds for a popular setting of ranking known as 'bipartite' ranking.

More from this channel