AI RESEARCH
Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand
arXiv CS.LG
•
ArXi:2605.05609v1 Announce Type: new We study contextual dynamic pricing with linear valuations and bounded- agnostic noise, whose induced demand curve may be non-Lipschitz with arbitrary jumps and atoms. Such discontinuities break the cross-context interpolation arguments used by smooth-demand pricing algorithms, while the best previous method achieved only $\tilde O(T^{3/4})$ regret. We propose Conservative-Markdown Redirect-UCB Pricing, a polynomial-time algorithm that combines randomized parameter estimation, conservative residual-grid probing, and confidence-based one-step redirection.