mlsanityData to 7 Oct 2026

Improved Algorithms for Contextual Dynamic Pricing

arXiv 2406.11316 ↗First posted 17 Jun 2024stat.ML cs.DS cs.GTcited by 11

Not on the map. Why?

Abstract (arXiv)

In contextual dynamic pricing, a seller sequentially prices goods based on contextual information. Buyers will purchase products only if the prices are below their valuations. The goal of the seller is to design a pricing strategy that collects as much revenue as possible. We focus on two different valuation models. The first assumes that valuations linearly depend on the context and are further distorted by noise. Under minor regularity assumptions, our algorithm achieves an optimal regret bound of tildeO(T2/3), improving the existing results. The second model removes the linearity assumption, requiring only that the expected buyer valuation is β-H"older in the context. For this model, our algorithm obtains a regret tildeO(Td+2β/d+3β), where d is the dimension of the context space.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 11 of its 33 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

11 of 33 references.

References · 11

  1. 2015Online Learning with Feedback Graphs: Beyond Banditscited by 79
  2. 2016Dynamic Pricing in High-dimensionscited by 55
  3. 2018Contextual Bandits with Cross-learningcited by 31
  4. 2018Dynamic Pricing with Finitely Many Unknown Valuationscited by 23
  5. 2020The Elliptical Potential Lemma Revisitedcited by 23
  6. 2021Policy Optimization Using Semi-parametric Models for Dynamic Pricingcited by 23
  7. 2021Distribution-free Contextual Dynamic Pricingcited by 22
  8. 2022Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noisecited by 21
  9. 2019Semi-parametric dynamic contextual pricingcited by 17
  10. 2024Optimal cross-learning for contextual bandits with unknown context distributionscited by 7
  11. 2020Online Regularization towards Always-Valid High-Dimensional Dynamic Pricingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 6.

11 papers.

  1. 2025Dynamic Pricing with Adversarially-Censored Demandscited by 4
  2. 2025Dynamic Pricing in the Linear Valuation Model using Shape Constraintscited by 3
  3. 2025Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shiftcited by 2
  4. 2026Efficient Adversarial Attacks on High-dimensional Offline Banditscited by 2
  5. 2026Nonparametric Contextual Online Bilateral Tradecited by 2
  6. 2026Optimal Contextual Pricing under Agnostic Non-Lipschitz Demandcited by 1
  7. 2025Contextual Learning for Stochastic Optimizationcited by 0
  8. 2025Online Linear Regression with Paid Stochastic Featurescited by 0
  9. 2026Learning to Attack: A Bandit Approach to Adversarial Context Poisoningcited by 0
  10. 2026NH-CROP: Robust Pricing for Governed Language Data Assets under Cost Uncertaintycited by 0
  11. 2026Adaptive Bandit Algorithms for Contextual Matching Marketscited by 0