ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2003.01703
21
1

Optimal Contextual Pricing and Extensions

3 March 2020
Allen Liu
R. Leme
Jon Schneider
ArXivPDFHTML
Abstract

In the contextual pricing problem a seller repeatedly obtains products described by an adversarially chosen feature vector in Rd\mathbb{R}^dRd and only observes the purchasing decisions of a buyer with a fixed but unknown linear valuation over the products. The regret measures the difference between the revenue the seller could have obtained knowing the buyer valuation and what can be obtained by the learning algorithm. We give a poly-time algorithm for contextual pricing with O(dlog⁡log⁡T+dlog⁡d)O(d \log \log T + d \log d)O(dloglogT+dlogd) regret which matches the Ω(dlog⁡log⁡T)\Omega(d \log \log T)Ω(dloglogT) lower bound up to the dlog⁡dd \log ddlogd additive factor. If we replace pricing loss by the symmetric loss, we obtain an algorithm with nearly optimal regret of O(dlog⁡d)O(d \log d)O(dlogd) matching the Ω(d)\Omega(d)Ω(d) lower bound up to log⁡d\log dlogd. These algorithms are based on a novel technique of bounding the value of the Steiner polynomial of a convex region at various scales. The Steiner polynomial is a degree ddd polynomial with intrinsic volumes as the coefficients. We also study a generalized version of contextual search where the hidden linear function over the Euclidean space is replaced by a hidden function f:X→Yf : \mathcal{X} \rightarrow \mathcal{Y}f:X→Y in a certain hypothesis class H\mathcal{H}H. We provide a generic algorithm with O(d2)O(d^2)O(d2) regret where ddd is the covering dimension of this class. This leads in particular to a O~(s2)\tilde{O}(s^2)O~(s2) regret algorithm for linear contextual search if the linear function is guaranteed to be sss-sparse. Finally we also extend our results to the noisy feedback model, where each round our feedback is flipped with a fixed probability p<1/2p < 1/2p<1/2.

View on arXiv
Comments on this paper