Ciliberto, C; Rudi, A; Rosasco, L; Pontil, M; (2017) Consistent multitask learning with nonlinear output relations. In: Guyon, I and Luxburg, U.V. and Bengio, S and Wallach, H and Fergus, R and Vishwanathan, S and Garnett., R, (eds.) Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017). (pp. pp. 1987-1997). Neural Information Processing Systems Foundation: California, Canada.

Preview

Text Ciliberto_nonlinear-output-relations.pdf - Accepted Version Download (671kB) | Preview

Abstract

Key to multitask learning is exploiting the relationships between different tasks in order to improve prediction performance. Most previous methods have focused on the case where tasks relations can be modeled as linear operators and regularization approaches can be used successfully. However, in practice assuming the tasks to be linearly related is often restrictive, and allowing for nonlinear structures is a challenge. In this paper, we tackle this issue by casting the problem within the framework of structured prediction. Our main contribution is a novel algorithm for learning multiple tasks which are related by a system of nonlinear equations that their joint outputs need to satisfy. We show that our algorithm can be efficiently implemented and study its generalization properties, proving universal consistency and learning rates. Our theoretical analysis highlights the benefits of non-linear multitask learning over learning the tasks independently. Encouraging experimental results show the benefits of the proposed method in practice.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as CSVXMLJSON

Downloads by country - last 12 months

Export as XMLCSVJSON

Archive Staff Only

View Item