Adaptive Oracle-Efficient Online LearningDownload PDF

Published: 31 Oct 2022, Last Modified: 15 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: online learning, oracle efficiency, adaptive online learning, small-loss bound
TL;DR: We provide an adaptive oracle-efficient online learning algorithm.
Abstract: The classical algorithms for online learning and decision-making have the benefit of achieving the optimal performance guarantees, but suffer from computational complexity limitations when implemented at scale. More recent sophisticated techniques, which we refer to as $\textit{oracle-efficient}$ methods, address this problem by dispatching to an $\textit{offline optimization oracle}$ that can search through an exponentially-large (or even infinite) space of decisions and select that which performed the best on any dataset. But despite the benefits of computational feasibility, most oracle-efficient algorithms exhibit one major limitation: while performing well in worst-case settings, they do not adapt well to friendly environments. In this paper we consider two such friendly scenarios, (a) "small-loss" problems and (b) IID data. We provide a new framework for designing follow-the-perturbed-leader algorithms that are oracle-efficient and adapt well to the small-loss environment, under a particular condition which we call $\textit{approximability}$ (which is spiritually related to sufficient conditions provided in (Dudík et al., 2020)). We identify a series of real-world settings, including online auctions and transductive online classification, for which approximability holds. We also extend the algorithm to an IID data setting and establish a "best-of-both-worlds" bound in the oracle-efficient setting.
Supplementary Material: pdf
12 Replies