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

arXiv: https://arxiv.org/abs/2505.17203 · HTML: https://mlsanity.com/paper/2505.17203/

## 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 (most cited first, 16 of 16)

- [Dynamic Pricing in High-dimensions](https://mlsanity.com/paper/1609.07574/) (2016)
- [Transfer Learning for Contextual Multi-armed Bandits](https://mlsanity.com/paper/2211.12612/) (2022)
- [Policy Optimization Using Semi-parametric Models for Dynamic Pricing](https://mlsanity.com/paper/2109.06368/) (2021)
- [Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise](https://mlsanity.com/paper/2201.11341/) (2022)
- [Multitask Learning and Bandits via Robust Statistics](https://mlsanity.com/paper/2112.14233/) (2021)
- [Improved Algorithms for Contextual Dynamic Pricing](https://mlsanity.com/paper/2406.11316/) (2024)
- [Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity](https://mlsanity.com/paper/2306.06291/) (2023)
- [Dynamic Contextual Pricing with Doubly Non-Parametric Random Utility Models](https://mlsanity.com/paper/2405.06866/) (2024)
- [Distributed Tensor Principal Component Analysis with Data Heterogeneity](https://mlsanity.com/paper/2405.11681/) (2024)
- [Fully Online Meta-Learning Without Task Boundaries](https://mlsanity.com/paper/2202.00263/) (2022)
- [Data-Driven Knowledge Transfer in Batch Q^* Learning](https://mlsanity.com/paper/2404.15209/) (2024)
- [Transfer Learning in Latent Contextual Bandits with Covariate Shift Through Causal Transportability](https://mlsanity.com/paper/2502.20153/) (2025)
- [Transfer Q-learning](https://mlsanity.com/paper/2202.04709/) (2022)
- [Deep Transfer Q-Learning for Offline Non-Stationary Reinforcement Learning](https://mlsanity.com/paper/2501.04870/) (2025)
- [Transition Transfer Q-Learning for Composite Markov Decision Processes](https://mlsanity.com/paper/2502.00534/) (2025)
- [Transfer Learning for Nonparametric Contextual Dynamic Pricing](https://mlsanity.com/paper/2501.18836/) (2025)

## Built on by (most cited first, 2 of 2)

- [One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RL](https://mlsanity.com/paper/2601.21924/) (2026)
- [Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints](https://mlsanity.com/paper/2605.19140/) (2026)

## 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.