Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction
Giulia Luise · Dimitrios Stamos · Massimiliano Pontil · Carlo Ciliberto

Tue Jun 11th 04:25 -- 04:30 PM @ Room 103

We study the interplay between surrogate methods for structured prediction and techniques from multitask learning designed to leverage relationships between surrogate outputs.
We propose an efficient algorithm based on trace norm regularization which, differently from previous methods, does not require explicit knowledge of the coding/decoding functions of the surrogate framework. As a result, our algorithm can be applied to the broad class of problems in which the surrogate space is large or even infinite dimensional. We study excess risk bounds for trace norm regularized structured prediction proving the consistency and learning rates for our estimator. We also identify relevant regimes in which our approach can enjoy better generalization performance than previous methods. Numerical experiments on ranking problems indicate that enforcing low-rank relations among surrogate outputs may indeed provide a significant advantage in practice.

Author Information

Giulia Luise (University College London)
Dimitrios Stamos (University College London)
Massimiliano Pontil (Istituto Italiano di Tecnologia and University College London)


Carlo Ciliberto (Imperial College London)

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

More from the Same Authors