Contextual Pandora's Box

Abstract

Pandora's Box is a fundamental stochastic optimization problem, where the decision-maker must find a good alternative while minimizing the search cost of exploring the value of each alternative. In the original formulation, it is assumed that accurate distributions are given for the values of all the alternatives, while recent work studies the online variant of Pandora's Box where the distributions are originally unknown. In this work, we study Pandora's Box in the online setting, while incorporating context. At every round, we are presented with a number of alternatives each having a context, an exploration cost and an unknown value drawn from an unknown distribution that may change at every round. Our main result is a no-regret algorithm that performs comparably well to the optimal algorithm which knows all prior distributions exactly. Our algorithm works even in the bandit setting where the algorithm never learns the values of the alternatives that were not explored. The key technique that enables our result is a novel modification of the realizability condition in contextual bandits that connects a context to a sufficient statistic of each alternative's distribution (its "reservation value") rather than its mean.

References in corpus (10)

• Improving Online Algorithms via ML Predictions
• Sparsity, variance and curvature in multi-armed bandits
• Revenue Optimization with Approximate Bid Predictions
• Scheduling with Predictions and the Price of Misprediction
• The entropic barrier: a simple and optimal universal self-concordant barrier
• Learning to Prune: Speeding up Repeated Computations
• Online Learning for Min Sum Set Cover and Pandora's Box
• Adaptivity Gaps for Stochastic Probing: Submodular and XOS Functions
• Bandit Algorithms for Prophet Inequality and Pandora's Box
• Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent

Cited by in corpus (1)

• Pandora's Box Problem With Time Constraints