Online Learning with Uncertain Feedback Graphs

TL;DR

This paper develops new online learning algorithms that effectively handle uncertainties in feedback graphs, enabling better decision-making with sublinear regret in expert advice scenarios.

Contribution

It introduces novel algorithms for online learning with uncertain feedback graphs, providing theoretical regret guarantees and demonstrating practical effectiveness.

Findings

Algorithms achieve sublinear regret under mild conditions.

Experimental results confirm the algorithms' effectiveness on real datasets.

Uncertainty in feedback graphs can be effectively managed with the proposed methods.

Abstract

Online learning with expert advice is widely used in various machine learning tasks. It considers the problem where a learner chooses one from a set of experts to take advice and make a decision. In many learning problems, experts may be related, henceforth the learner can observe the losses associated with a subset of experts that are related to the chosen one. In this context, the relationship among experts can be captured by a feedback graph, which can be used to assist the learner's decision making. However, in practice, the nominal feedback graph often entails uncertainties, which renders it impossible to reveal the actual relationship among experts. To cope with this challenge, the present work studies various cases of potential uncertainties, and develops novel online learning algorithms to deal with uncertainties while making use of the uncertain feedback graph. The proposed algorithms are proved to enjoy sublinear regret under mild conditions. Experiments on real datasets are presented to demonstrate the effectiveness of the novel algorithms.