Fast Rates for Nonparametric Online Learning: From Realizability to Learning in Games

TL;DR

This paper develops new algorithms for nonparametric online learning that achieve near-optimal convergence rates and applies these results to learning in games, improving upon previous bounds.

Contribution

It introduces a randomized proper learning algorithm with near-optimal loss bounds and applies it to general-sum binary games, achieving improved regret bounds.

Findings

Proper learners achieve near-optimal cumulative loss in nonparametric online regression.

New regret bounds of (d^{3/4} \, T^{1/4}) for players in general-sum binary games.

Hierarchical aggregation and stability techniques are introduced for nonparametric online learning.

Abstract

We study fast rates of convergence in the setting of nonparametric online regression, namely where regret is defined with respect to an arbitrary function class which has bounded complexity. Our contributions are two-fold: - In the realizable setting of nonparametric online regression with the absolute loss, we propose a randomized proper learning algorithm which gets a near-optimal cumulative loss in terms of the sequential fat-shattering dimension of the hypothesis class. In the setting of online classification with a class of Littlestone dimension $d$, our bound reduces to $d \cdot {\rm poly} \log T$. This result answers a question as to whether proper learners could achieve near-optimal cumulative loss; previously, even for online classification, the best known cumulative loss was $\tilde O( \sqrt{dT})$. Further, for the real-valued (regression) setting, a cumulative loss bound with near-optimal scaling on sequential fat-shattering dimension was not even known for improper learners, prior to this work. - Using the above result, we exhibit an independent learning algorithm for general-sum binary games of Littlestone dimension $d$, for which each player achieves regret $\tilde O(d^{3/4} \cdot T^{1/4})$. This result generalizes analogous results of Syrgkanis et al. (2015) who showed that in finite games the optimal regret can be accelerated from $O(\sqrt{T})$ in the adversarial setting to $O(T^{1/4})$ in the game setting. To establish the above results, we introduce several new techniques, including: a hierarchical aggregation rule to achieve the optimal cumulative loss for real-valued classes, a multi-scale extension of the proper online realizable learner of Hanneke et al. (2021), an approach to show that the output of such nonparametric learning algorithms is stable, and a proof that the minimax theorem holds in all online learnable games.