mlsanityData to 14 Oct 2026

Contextual Online Pricing with (Biased) Offline Data

arXiv 2507.02762 ↗First posted 3 Jul 2025cs.LG stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

We study contextual online pricing with biased offline data. For the scalar price elasticity case, we identify the instance-dependent quantity δ2 that measures how far the offline data lies from the (unknown) online optimum. We show that the time length T, bias bound V, size N and dispersion λmin(hatSigma) of the offline data, and δ2 jointly determine the statistical complexity. An Optimism-in-the-Face-of-Uncertainty (OFU) policy achieves a minimax-optimal, instance-dependent regret bound tildeObig(d√T wedge (V2T + fracdTλmin(hatSigma) + (N wedge T) δ2)big). For general price elasticity, we establish a worst-case, minimax-optimal rate tildeObig(d√T wedge (V2T + fracdT λmin(hatSigma))big) and provide a generalized OFU algorithm that attains it. When the bias bound V is unknown, we design a robust variant that always guarantees sub-linear regret and strictly improves on purely online methods whenever the exact bias is small. These results deliver the first tight regret guarantees for contextual pricing in the presence of biased offline data. Our techniques also transfer verbatim to stochastic linear bandits with biased offline data, yielding analogous bounds.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 15 of its 35 references that are in the map. First posted on arXiv 3 Jul 2025.

Builds on

15 of 35 references.

References · 15

  1. 2015An Introduction to Matrix Concentration Inequalitiescited by 397
  2. 2020Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifierscited by 97
  3. 2021Meta-Thompson Samplingcited by 63
  4. 2021Bayesian decision-making under misspecified priors with applications to meta-learningcited by 44
  5. 2022Leveraging Offline Data in Online Reinforcement Learningcited by 42
  6. 2016Dynamic Pricing with Demand Covariatescited by 31
  7. 2019Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedbackcited by 21
  8. 2020Taking a hint: How to leverage loss predictors in contextual bandits?cited by 20
  9. 2015On the Prior Sensitivity of Thompson Samplingcited by 15
  10. 2025Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewardscited by 14
  11. 2019Online Pricing with Offline Data: Phase Transition and Inverse Square Lawcited by 13
  12. 2024Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Datacited by 8
3 more
  1. 2022Data-pooling Reinforcement Learning for Personalized Healthcare Interventioncited by 6
  2. 2020Combining Offline Causal Inference and Online Bandit Learning for Data Driven Decisioncited by 5
  3. 2024Provable Domain Adaptation for Offline Reinforcement Learning with Limited Samplescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Direction-Aware Offline-to-Online Learning in Linear Contextual Banditscited by 1
  2. 2026Best-Arm Identification with Generative Proxycited by 1
  3. 2026Offline-Online Reinforcement Learning for Linear Mixture MDPscited by 0
  4. 2026Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shiftcited by 0