English

Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback

Machine Learning 2023-06-02 v2 Machine Learning

Abstract

We consider the linear contextual multi-class multi-period packing problem (LMMP) where the goal is to pack items such that the total vector of consumption is below a given budget vector and the total value is as large as possible. We consider the setting where the reward and the consumption vector associated with each action is a class-dependent linear function of the context, and the decision-maker receives bandit feedback. LMMP includes linear contextual bandits with knapsacks and online revenue management as special cases. We establish a new estimator which guarantees a faster convergence rate, and consequently, a lower regret in such problems. We propose a bandit policy that is a closed-form function of said estimated parameters. When the contexts are non-degenerate, the regret of the proposed policy is sublinear in the context dimension, the number of classes, and the time horizon TT when the budget grows at least as T\sqrt{T}. We also resolve an open problem posed by Agrawal & Devanur (2016) and extend the result to a multi-class setting. Our numerical experiments clearly demonstrate that the performance of our policy is superior to other benchmarks in the literature.

Keywords

Cite

@article{arxiv.2301.13791,
  title  = {Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback},
  author = {Wonyoung Kim and Garud Iyengar and Assaf Zeevi},
  journal= {arXiv preprint arXiv:2301.13791},
  year   = {2023}
}

Comments

Accepted in ICML 2023, 44 pages including Appendix

R2 v1 2026-06-28T08:28:16.304Z