Learning the learning rate for prediction with expert advice

Koolen, Wouter M., van Erven, Tim, & Grünwald, Peter D. (2014) Learning the learning rate for prediction with expert advice. In Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., & Weinberger, K.Q. (Eds.) Advances in Neural Information Processing Systems 27 (NIPS 2014), Neural Information Processing Systems Foundation, Inc., Montreal, Quebec, Canada, pp. 2294-2302.

View at publisher (open access)


Most standard algorithms for prediction with expert advice depend on a parameter called the learning rate. This learning rate needs to be large enough to fit the data well, but small enough to prevent overfitting. For the exponential weights algorithm, a sequence of prior work has established theoretical guarantees for higher and higher data-dependent tunings of the learning rate, which allow for increasingly aggressive learning. But in practice such theoretical tunings often still perform worse (as measured by their regret) than ad hoc tuning with an even higher learning rate. To close the gap between theory and practice we introduce an approach to learn the learning rate. Up to a factor that is at most (poly)logarithmic in the number of experts and the inverse of the learning rate, our method performs as well as if we would know the empirically best learning rate from a large range that includes both conservative small values and values that are much higher than those for which formal guarantees were previously available. Our method employs a grid of learning rates, yet runs in linear time regardless of the size of the grid.

Impact and interest:

5 citations in Scopus
Search Google Scholar™

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

Full-text downloads:

39 since deposited on 12 Mar 2015
15 in the past twelve months

Full-text downloads displays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.

ID Code: 82486
Item Type: Conference Paper
Refereed: No
Divisions: Current > QUT Faculties and Divisions > Science & Engineering Faculty
Copyright Owner: Copyright 2014 [please consult the authors]
Deposited On: 12 Mar 2015 23:23
Last Modified: 24 Jun 2017 08:02

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page