Adaptive Algorithms for Meta-Induction-Reference-Cited by-同舟云学术

Adaptive Algorithms for Meta-Induction

Published:2022-10-07 Issue: Volume: Page:
ISSN:0925-4560
Container-title:Journal for General Philosophy of Science
language:en
Short-container-title:J Gen Philos Sci

Author:

Ortner Ronald^ORCID

Abstract

AbstractWork in online learning traditionally considered induction-friendly (e.g. stochastic with a fixed distribution) and induction-hostile (adversarial) settings separately. While algorithms like Exp3 that have been developed for the adversarial setting are applicable to the stochastic setting as well, the guarantees that can be obtained are usually worse than those that are available for algorithms that are specifically designed for stochastic settings. Only recently, there is an increasing interest in algorithms that give (near-)optimal guarantees with respect to the underlying setting, even in case its nature is unknown to the learner. In this paper, we review various online learning algorithms that are able to adapt to the hardness of the underlying problem setting. While our focus lies on the application of adaptive algorithms as meta-inductive methods that combine given base methods, concerning theoretical properties we are also interested in guarantees that go beyond a comparison to the best fixed base learner.

Funder

FWF

Montanuniversität Leoben

Publisher

Springer Science and Business Media LLC

Subject

History and Philosophy of Science,General Social Sciences,Philosophy

Link

https://link.springer.com/content/pdf/10.1007/s10838-021-09590-2.pdf

Reference31 articles.

1. Abbasi-Yadkori, Y., Bartlett, P. L., Gabillon, V., Malek, A., & Valko, M. (2018). Best of both worlds: Stochastic & adversarial best-arm identification. In Conference on learning theory, COLT 2018, volume 75 of Proceedings of machine learning research (pp. 918–949).

2. Agarwal, A., Luo, H., Neyshabur, B., & Schapire, R. E. (2017). Corralling a band of bandit algorithms. In Proceedings of the 30th conference on learning theory, COLT 2017, volume 65 of Proceedings of machine learning research (pp. 12–38).

3. Arora, S., Hazan, E., & Kale, S. (2012). The multiplicative weights update method: A meta-algorithm and applications. Theory of Computing, 8(1), 121–164.

4. Audibert, J.-Y., & Bubeck, S. (2010). Regret bounds and minimax policies under partial monitoring. Journal of Machine Learning Research, 11, 2785–2836.

5. Auer, P., & Chiang, C.-K. (2016). An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits. In Proceedings of the 29th conference on learning theory, COLT 2016, volume 49 of Proceedings of machine learning research (pp. 116–120).