English

A Multi-Arm Bandit Approach To Subset Selection Under Constraints

Machine Learning 2021-02-10 v1

Abstract

We explore the class of problems where a central planner needs to select a subset of agents, each with different quality and cost. The planner wants to maximize its utility while ensuring that the average quality of the selected agents is above a certain threshold. When the agents' quality is known, we formulate our problem as an integer linear program (ILP) and propose a deterministic algorithm, namely \dpss\ that provides an exact solution to our ILP. We then consider the setting when the qualities of the agents are unknown. We model this as a Multi-Arm Bandit (MAB) problem and propose \newalgo\ to learn the qualities over multiple rounds. We show that after a certain number of rounds, τ\tau, \newalgo\ outputs a subset of agents that satisfy the average quality constraint with a high probability. Next, we provide bounds on τ\tau and prove that after τ\tau rounds, the algorithm incurs a regret of O(lnT)O(\ln T), where TT is the total number of rounds. We further illustrate the efficacy of \newalgo\ through simulations. To overcome the computational limitations of \dpss, we propose a polynomial-time greedy algorithm, namely \greedy, that provides an approximate solution to our ILP. We also compare the performance of \dpss\ and \greedy\ through experiments.

Keywords

Cite

@article{arxiv.2102.04824,
  title  = {A Multi-Arm Bandit Approach To Subset Selection Under Constraints},
  author = {Ayush Deva and Kumar Abhishek and Sujit Gujar},
  journal= {arXiv preprint arXiv:2102.04824},
  year   = {2021}
}

Comments

Accepted in AAMAS 2021 as Extended Abstract

R2 v1 2026-06-23T22:58:49.693Z