[edit]
Smoothness-Adaptive Dynamic Pricing with Nonparametric Demand Learning
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR 238:1675-1683, 2024.
Abstract
We study the dynamic pricing problem where the demand function is nonparametric and Hölder smooth, and we focus on adaptivity to the unknown Hölder smoothness parameter β of the demand function. Traditionally the optimal dynamic pricing algorithm heavily relies on the knowledge of β to achieve a minimax optimal regret of ˜O(Tβ+12β+1). However, we highlight the challenge of adaptivity in this dynamic pricing problem by proving that no pricing policy can adaptively achieve this minimax optimal regret without knowledge of β. Motivated by the impossibility result, we propose a self-similarity condition to enable adaptivity. Importantly, we show that the self-similarity condition does not compromise the problem’s inherent complexity since it preserves the regret lower bound Ω(Tβ+12β+1). Furthermore, we develop a smoothness-adaptive dynamic pricing algorithm and theoretically prove that the algorithm achieves this minimax optimal regret bound without the prior knowledge β.