PulseAugur
LIVE 08:26:56
research · [2 sources] ·
0
research

New algorithm achieves optimal regret in contextual pricing with non-Lipschitz demand

Researchers have developed a new algorithm called Conservative-Markdown Redirect-UCB Pricing to address contextual dynamic pricing challenges. This algorithm is designed to handle demand curves that are non-Lipschitz, featuring arbitrary jumps and atoms, which previously hindered pricing algorithms. The new method achieves an optimal regret of \tilde O(T^{2/3}), improving upon prior methods and closing a gap in theoretical understanding for linear-valuation contextual pricing. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Improves theoretical understanding of pricing algorithms in complex demand scenarios, potentially impacting e-commerce and recommendation systems.

RANK_REASON This is a research paper published on arXiv detailing a new algorithm for contextual pricing.

Read on arXiv stat.ML →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 · Jianyu Xu, Yu-Xiang Wang ·

    Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand

    arXiv:2605.05609v1 Announce Type: new Abstract: We study contextual dynamic pricing with linear valuations and bounded-support agnostic noise, whose induced demand curve may be non-Lipschitz with arbitrary jumps and atoms. Such discontinuities break the cross-context interpolatio…

  2. arXiv stat.ML TIER_1 · Yu-Xiang Wang ·

    Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand

    We study contextual dynamic pricing with linear valuations and bounded-support 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 algori…