UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Regret Bounds for Lifelong Learning

Alquier, P; Mai, TT; Pontil, M; (2017) Regret Bounds for Lifelong Learning. In: Singh, A and Zhu, XJ, (eds.) Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017). (pp. pp. 261-269). PMLR (Proceedings of Machine Learning Research): Fort Lauderdale, FL, USA. Green open access

[img]
Preview
Text
alquier17a.pdf - Published version

Download (469kB) | Preview

Abstract

We consider the problem of transfer learning in an online setting. Di↵erent tasks are presented sequentially and processed by a within-task algorithm. We propose a lifelong learning strategy which refines the underlying data representation used by the withintask algorithm, thereby transferring information from one task to the next. We show that when the within-task algorithm comes with some regret bound, our strategy inherits this good property. Our bounds are in expectation for a general loss function, and uniform for a convex loss. We discuss applications to dictionary learning and finite set of predictors. In the latter case, we improve previous O(1/pm) bounds to O(1/m), where m is the per task sample size.

Type: Proceedings paper
Title: Regret Bounds for Lifelong Learning
Event: 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017), 20-22 April 2017, Fort Lauderdale, FL, USA
Open access status: An open access version is available from UCL Discovery
Publisher version: http://jmlr.org/proceedings/papers/v54/
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10073437
Downloads since deposit
5Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item