Batch-Size Independent Regret Bounds for the Combinatorial Multi-Armed Bandit Problem

Abstract

We consider the combinatorial multi-armed bandit (CMAB) problem, where the reward function is nonlinear. In this setting, the agent chooses a batch of arms on each round and receives feedback from each arm of the batch. The reward that the agent aims to maximize is a function of the selected arms and their expectations. In many applications, the reward function is highly nonlinear, and the performance of existing algorithms relies on a global Lipschitz constant to encapsulate the function's nonlinearity. This may lead to loose regret bounds, since by itself, a large gradient does not necessarily cause a large regret, but only in regions where the uncertainty in the reward's parameters is high. To overcome this problem, we introduce a new smoothness criterion, which we term \emph{Gini-weighted smoothness}, that takes into account both the nonlinearity of the reward and concentration properties of the arms. We show that a linear dependence of the regret in the batch size in existing algorithms can be replaced by this smoothness parameter. This, in turn, leads to much tighter regret bounds when the smoothness parameter is batch-size independent. For example, in the probabilistic maximum coverage (PMC) problem, that has many applications, including influence maximization, diverse recommendations and more, we achieve dramatic improvements in the upper bounds. We also prove matching lower bounds for the PMC problem and show that our algorithm is tight, up to a logarithmic factor in the problem's parameters.

arXiv commentAccepted to COLT 2019

References in corpus (15)

• (More) Efficient Reinforcement Learning via Posterior Sampling
• Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits
• Combinatorial Bandits Revisited
• Combinatorial Multi-Armed Bandit and Its Extension to Probabilistically Triggered Arms
• Cascading Bandits: Learning to Rank in the Cascade Model
• Matroid Bandits: Fast Combinatorial Optimization with Learning
• Combinatorial Multi-Armed Bandit with General Reward Functions
• Combinatorial Cascading Bandits
• Thompson Sampling for Combinatorial Semi-Bandits
• TopRank: A practical algorithm for online stochastic ranking
• Improving Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms and Its Applications
• Influence Maximization with Bandits
• Combinatorial semi-bandit with known covariance
• Efficient-UCBV: An Almost Optimal Algorithm using Variance Estimates
• Revealing graph bandits for maximizing local influence