eprintid: 10077127 rev_number: 22 eprint_status: archive userid: 608 dir: disk0/10/07/71/27 datestamp: 2019-09-05 19:00:20 lastmod: 2021-11-23 23:31:13 status_changed: 2019-09-05 19:00:20 type: article metadata_visibility: show creators_name: Luise, G creators_name: Stamos, D creators_name: Pontil, M creators_name: Ciliberto, C title: Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 note: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. abstract: 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, implying 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. date: 2019 official_url: http://proceedings.mlr.press/v97/luise19a.html oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1640591 lyricists_name: Ciliberto, Carlo lyricists_name: Luise, Giulia lyricists_name: Pontil, Massimiliano lyricists_id: CCILI30 lyricists_id: GLUIS61 lyricists_id: MPONT27 actors_name: Pontil, Massimiliano actors_id: MPONT27 actors_role: owner full_text_status: public publication: Proceedings of the 36th International Conference on Machine Learning volume: 97 pagerange: 4193-4202 citation: Luise, G; Stamos, D; Pontil, M; Ciliberto, C; (2019) Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction. Proceedings of the 36th International Conference on Machine Learning , 97 pp. 4193-4202. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10077127/1/luise19a.pdf