mlsanityData to 14 Oct 2026

Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift

arXiv 2505.17203 ↗First posted 22 May 2025stat.ME cs.LG stat.APcited by 2

Not on the map. Why?

Abstract (arXiv)

We study contextual dynamic pricing when a target market can leverage K auxiliary markets -- offline logs or concurrent streams -- whose mean utilities differ by a structured preference shift. We propose Cross-Market Transfer Dynamic Pricing (CM-TDP), the first algorithm that provably handles such model-shift transfer and delivers minimax-optimal regret for both linear and non-parametric utility models. For linear utilities of dimension d, where the difference between source- and target-task coefficients is s0-sparse, CM-TDP attains regret tildeO((d*K-1+s0)log T). For nonlinear demand residing in a reproducing kernel Hilbert space with effective dimension α, complexity β and task-similarity parameter H, the regret becomes tildeO!(K-2αβ/(2αβ+1)T1/(2αβ+1) + H2/(2α+1)T1/(2α+1)), matching information-theoretic lower bounds up to logarithmic factors. The RKHS bound is the first of its kind for transfer pricing and is of independent interest. Extensive simulations show up to 50% lower cumulative regret and 5 times faster learning relative to single-market pricing baselines. By bridging transfer learning, robust aggregation, and revenue optimization, CM-TDP moves toward pricing systems that transfer faster, price smarter.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 37 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

16 of 37 references.

References · 16

  1. 2016Dynamic Pricing in High-dimensionscited by 55
  2. 2022Transfer Learning for Contextual Multi-armed Banditscited by 24
  3. 2021Policy Optimization Using Semi-parametric Models for Dynamic Pricingcited by 23
  4. 2022Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noisecited by 21
  5. 2021Multitask Learning and Bandits via Robust Statisticscited by 11
  6. 2024Improved Algorithms for Contextual Dynamic Pricingcited by 11
  7. 2023Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneitycited by 7
  8. 2024Dynamic Contextual Pricing with Doubly Non-Parametric Random Utility Modelscited by 6
  9. 2024Distributed Tensor Principal Component Analysis with Data Heterogeneitycited by 6
  10. 2022Fully Online Meta-Learning Without Task Boundariescited by 4
  11. 2024Data-Driven Knowledge Transfer in Batch Q^* Learningcited by 4
  12. 2025Transfer Learning in Latent Contextual Bandits with Covariate Shift Through Causal Transportabilitycited by 4
4 more
  1. 2022Transfer Q-learningcited by 3
  2. 2025Deep Transfer Q-Learning for Offline Non-Stationary Reinforcement Learningcited by 3
  3. 2025Transition Transfer Q-Learning for Composite Markov Decision Processescited by 2
  4. 2025Transfer Learning for Nonparametric Contextual Dynamic Pricingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RLcited by 1
  2. 2026Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraintscited by 1