Diversity-Preserving K-Armed Bandits, Revisited

Abstract

We consider the bandit-based framework for diversity-preserving recommendations introduced by Celis et al. (2019), who approached it in the case of a polytope mainly by a reduction to the setting of linear bandits. We design a UCB algorithm using the specific structure of the setting and show that it enjoys a bounded distribution-dependent regret in the natural cases when the optimal mixed actions put some probability mass on all actions (i.e., when diversity is desirable). The regret lower bounds provided show that otherwise, at least when the model is mean-unbounded, a $\ln T$ regret is suffered. We also discuss an example beyond the special case of polytopes.

References in corpus (8)

• A Contextual-Bandit Approach to Personalized News Article Recommendation
• Bounded Regret for Finite-Armed Structured Bandits
• Online Learning with an Unknown Fairness Metric
• Linear Stochastic Bandits Under Safety Constraints
• Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality
• Bandits with Side Observations: Bounded vs. Logarithmic Regret
• A Novel Confidence-Based Algorithm for Structured Bandits
• Achieving Fairness in Stochastic Multi-armed Bandit Problem