<ul data-eligibleForWebStory="true"><li>Study examines multi-armed bandits with network interference affecting rewards based on local graph structure.</li><li>Proposed algorithm leverages graph characteristics to reduce regret in exponentially large action spaces.</li><li>A graph-dependent upper bound on cumulative regret is achieved, surpassing previous research.</li><li>Lower bounds for bandits with diverse network interference types are established using graph properties.</li><li>Algorithm's optimality is demonstrated for dense and sparse graphs with near-optimal performance.</li><li>In cases of unknown interference graph, algorithm variant is Pareto optimal, leading in all scenarios.</li><li>Theoretical findings are supported by numerical experiments, illustrating superior performance over standard methods.</li></ul>

Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference

Discover more