Spectrum Bandit Optimization

TL;DR

This paper addresses the challenge of allocating radio channels in wireless networks to maximize throughput, formulating it as a linear bandit problem and developing algorithms with regret bounds in both stochastic and adversarial scenarios.

Contribution

It introduces a novel linear bandit framework for spectrum allocation, providing new algorithms and regret analysis for both stochastic and adversarial radio condition models.

Findings

Algorithms achieve sublinear regret bounds.

Effective in both stochastic and adversarial environments.

Provides theoretical guarantees for spectrum bandit optimization.

Abstract

We consider the problem of allocating radio channels to links in a wireless network. Links interact through interference, modelled as a conflict graph (i.e., two interfering links cannot be simultaneously active on the same channel). We aim at identifying the channel allocation maximizing the total network throughput over a finite time horizon. Should we know the average radio conditions on each channel and on each link, an optimal allocation would be obtained by solving an Integer Linear Program (ILP). When radio conditions are unknown a priori, we look for a sequential channel allocation policy that converges to the optimal allocation while minimizing on the way the throughput loss or {\it regret} due to the need for exploring sub-optimal allocations. We formulate this problem as a generic linear bandit problem, and analyze it first in a stochastic setting where radio conditions are driven by a stationary stochastic process, and then in an adversarial setting where radio conditions can evolve arbitrarily. We provide new algorithms in both settings and derive upper bounds on their regrets.