Continuum-armed Bandit Optimization with Batch Pairwise Comparison Oracles

TL;DR

This paper introduces a novel bandit optimization approach using pairwise comparison oracles with biased estimates, applying it to pricing, inventory, and revenue management, and achieves near-optimal regret bounds.

Contribution

It develops a new algorithm combining discretization, local polynomial approximation, and a tournament elimination method for pairwise comparison bandits with biased feedback.

Findings

Achieves regret bounds close to the theoretical optimum.

Improves existing results in inventory and revenue management applications.

Introduces a new framework for biased pairwise comparison oracles.

Abstract

This paper studies a bandit optimization problem where the goal is to maximize a function $f(x)$ over $T$ periods for some unknown strongly concave function $f$. We consider a new pairwise comparison oracle, where the decision-maker chooses a pair of actions $(x, x')$ for a consecutive number of periods and then obtains an estimate of $f(x)-f(x')$. We show that such a pairwise comparison oracle finds important applications to joint pricing and inventory replenishment problems and network revenue management. The challenge in this bandit optimization is twofold. First, the decision-maker not only needs to determine a pair of actions $(x, x')$ but also a stopping time $n$ (i.e., the number of queries based on $(x, x')$). Second, motivated by our inventory application, the estimate of the difference $f(x)-f(x')$ is biased, which is different from existing oracles in stochastic optimization literature. To address these challenges, we first introduce a discretization technique and local polynomial approximation to relate this problem to linear bandits. Then we developed a tournament successive elimination technique to localize the discretized cell and run an interactive batched version of LinUCB algorithm on cells. We establish regret bounds that are optimal up to poly-logarithmic factors. Furthermore, we apply our proposed algorithm and analytical framework to the two operations management problems and obtain results that improve state-of-the-art results in the existing literature.