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

Online Parameter-Free Learning of Multiple Low Variance Tasks

Denevi, G; Pontil, M; Stamos, D; (2020) Online Parameter-Free Learning of Multiple Low Variance Tasks. In: Adams, RP and Gogate, V, (eds.) Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI). AUAI Press: Virtual conference. Green open access

[img]
Preview
Text
368_main_paper.pdf - Published version

Download (529kB) | Preview

Abstract

We propose a method to learn a common bias vector for a growing sequence of low-variance tasks. Unlike state-of-the-art approaches, our method does not require tuning any hyper-parameter. Our approach is presented in the non-statistical setting and can be of two variants. The “aggressive” one updates the bias after each datapoint, the “lazy” one updates the bias only at the end of each task. We derive an across-tasks regret bound for the method. When compared to state-of-the-art approaches, the aggressive variant returns faster rates, the lazy one recovers standard rates, but with no need of tuning hyper-parameters. We then adapt the methods to the statistical setting: the aggressive variant becomes a multi-task learning method, the lazy one a meta-learning method. Experiments confirm the effectiveness of our methods in practice.

Type: Proceedings paper
Title: Online Parameter-Free Learning of Multiple Low Variance Tasks
Event: 36th Conference on Uncertainty in Artificial Intelligence (UAI)
Open access status: An open access version is available from UCL Discovery
Publisher version: http://auai.org/uai2020/accepted.php
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
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/10112125
Downloads since deposit
9Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item