@inproceedings{8130edf2db8a4af881bffb330b925dcc,
title = "Best-of-All-Worlds Bounds for Online Learning with Feedback Graphs",
abstract = "We study the online learning with feedback graphs framework introduced by Mannor and Shamir [24], in which the feedback received by the online learner is specified by a graph G over the available actions. We develop an algorithm that simultaneously achieves regret bounds of the form: (equation presented) O(√θ(G)T) with adversarial losses; O(θ(G) polylogT) with stochastic losses; and O(θ(G) polylogT +pθ(G)C) with stochastic losses subject to C adversarial corruptions. Here, θ(G) is the clique covering number of the graph G. Our algorithm is an instantiation of Follow-the-Regularized-Leader with a novel regularization that can be seen as a product of a Tsallis entropy component (inspired by Zimmert and Seldin [27]) and a Shannon entropy component (analyzed in the corrupted stochastic case by Amir et al. [3]), thus subtly interpolating between the two forms of entropies. One of our key technical contributions is in establishing the convexity of this regularizer and controlling its inverse Hessian, despite its complex product structure.",
author = "Liad Erez and Tomer Koren",
note = "Publisher Copyright: {\textcopyright} 2021 Neural information processing systems foundation. All rights reserved.; 35th Conference on Neural Information Processing Systems, NeurIPS 2021 ; Conference date: 06-12-2021 Through 14-12-2021",
year = "2021",
language = "الإنجليزيّة",
series = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",
pages = "28511--28521",
editor = "Marc'Aurelio Ranzato and Alina Beygelzimer and Yann Dauphin and Liang, \{Percy S.\} and \{Wortman Vaughan\}, Jenn",
booktitle = "Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021",
address = "الولايات المتّحدة",
}