Skip to content

Opening book details…

Can I read Contextual Combinatorial Multi-output GP Bandits with Group Constraints on EtoBox?

Contextual Combinatorial Multi-output GP Bandits with Group Constraints by Elahi, Sepehr; Atalar, Baran; Öğüt, Sevda; Tekin, Cem is a scholarly article available to read on EtoBox.

What is Contextual Combinatorial Multi-output GP Bandits with Group Constraints about?

In federated multi-armed bandit problems, maximizing global reward while satisfying minimum privacy requirements to protect clients is the main goal. To formulate such problems, we consider a combinatorial contextual bandit setting with groups and changing action sets, where similar base arms arrive in groups and a set of base arms, called a super arm, must be chosen in each round to maximize super arm reward while satisfying the constraints of the rewards of groups from which base arms were chosen. To allow for greater flexibility, we let each base arm have two outcomes, modeled as the output of a two-output Gaussian process (GP), where one outcome is used to compute super arm reward and the other for group reward. We then propose a novel double-UCB GP-bandit algorithm, called Thresholded Combinatorial Gaussian Process Upper Confidence Bounds (TCGP-UCB), which balances between maximizing cumulative super arm reward and satisfying group reward constraints and can be tuned to prefer one over the other. We also define a new notion of regret that combines super arm regret with group reward constraint satisfaction and prove that TCGP-UCB incurs $\tilde{O}(\sqrt{\lambda^*(K)KT\overline{

Author
Elahi, Sepehr; Atalar, Baran; Öğüt, Sevda; Tekin, Cem
Published
2021
Language
EN

More by Elahi, Sepehr; Atalar, Baran; Öğüt, Sevda; Tekin, Cem

Browse all works by Elahi, Sepehr; Atalar, Baran; Öğüt, Sevda; Tekin, Cem