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

Meta-Strategy for Learning Tuning Parameters with Guarantees

Meunier, Dimitri; Alquier, Pierre; (2021) Meta-Strategy for Learning Tuning Parameters with Guarantees. Entropy , 23 (10) , Article 1257. 10.3390/e23101257. Green open access

[thumbnail of entropy-23-01257-v2.pdf]
Preview
Text
entropy-23-01257-v2.pdf - Published Version

Download (593kB) | Preview

Abstract

Online learning methods, similar to the online gradient algorithm (OGA) and exponentially weighted aggregation (EWA), often depend on tuning parameters that are difficult to set in practice. We consider an online meta-learning scenario, and we propose a meta-strategy to learn these parameters from past tasks. Our strategy is based on the minimization of a regret bound. It allows us to learn the initialization and the step size in OGA with guarantees. It also allows us to learn the prior or the learning rate in EWA. We provide a regret analysis of the strategy. It allows to identify settings where meta-learning indeed improves on learning each task in isolation.

Type: Article
Title: Meta-Strategy for Learning Tuning Parameters with Guarantees
Open access status: An open access version is available from UCL Discovery
DOI: 10.3390/e23101257
Publisher version: https://doi.org/10.3390/e23101257
Language: English
Additional information: This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third-party material in this article are included in the Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/
Keywords: Meta-learning; hyperparameters; priors; online learning; Bayesian inference; online optimization; gradient descent
UCL classification: UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neurosci Unit
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL
URI: https://discovery.ucl.ac.uk/id/eprint/10150499
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