Timezone: »

Convex Calibrated Surrogates for Low-Rank Loss Matrices with Applications to Subset Ranking Losses
Harish G Ramaswamy · Shivani Agarwal · Ambuj Tewari

Sat Dec 07 07:00 PM -- 11:59 PM (PST) @ Harrah's Special Events Center, 2nd Floor

The design of convex, calibrated surrogate losses, whose minimization entails consistency with respect to a desired target loss, is an important concept to have emerged in the theory of machine learning in recent years. We give an explicit construction of a convex least-squares type surrogate loss that can be designed to be calibrated for any multiclass learning problem for which the target loss matrix has a low-rank structure; the surrogate loss operates on a surrogate target space of dimension at most the rank of the target loss. We use this result to design convex calibrated surrogates for a variety of subset ranking problems, with target losses including the precision@q, expected rank utility, mean average precision, and pairwise disagreement.

Author Information

Harish G Ramaswamy (Indian Institute of Science)
Shivani Agarwal (University of Pennsylvania)
Ambuj Tewari (University of Michigan)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors