# Differential Privacy in Personalized Pricing with Nonparametric Demand Models

arXiv: https://arxiv.org/abs/2109.04615 · HTML: https://mlsanity.com/paper/2109.04615/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 63 references that are in the map.
- First posted on arXiv 10 Sep 2021.

## Builds on (most cited first, 11 of 11)

- [Minimax Optimal Procedures for Locally Private Estimation](https://mlsanity.com/paper/1604.02390/) (2016)
- [Differentially Private Contextual Linear Bandits](https://mlsanity.com/paper/1810.00068/) (2018)
- [Dynamic Pricing in High-dimensions](https://mlsanity.com/paper/1609.07574/) (2016)
- [Locally Differentially Private (Contextual) Bandits Learning](https://mlsanity.com/paper/2006.00701/) (2020)
- [Multi-Armed Bandits with Local Differential Privacy](https://mlsanity.com/paper/2007.03121/) (2020)
- [Dynamic Pricing with Demand Covariates](https://mlsanity.com/paper/1604.07463/) (2016)
- [Generalized Linear Bandits with Local Differential Privacy](https://mlsanity.com/paper/2106.03365/) (2021)
- [Privacy-Preserving Dynamic Personalized Pricing with Demand Learning](https://mlsanity.com/paper/2009.12920/) (2020)
- [Uncertainty Quantification for Demand Prediction in Contextual Dynamic Pricing](https://mlsanity.com/paper/2003.07017/) (2020)
- [Private Sequential Learning](https://mlsanity.com/paper/1805.02136/) (2018)
- [Query Complexity of Bayesian Private Learning](https://mlsanity.com/paper/1911.06903/) (2019)

## Built on by (most cited first, 13 of 13)

- [Optimal and Differentially Private Data Acquisition: Central and Local Mechanisms](https://mlsanity.com/paper/2201.03968/) (2022)
- [On Private and Robust Bandits](https://mlsanity.com/paper/2302.02526/) (2023)
- [Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards](https://mlsanity.com/paper/2306.01121/) (2023)
- [Utility Fairness in Contextual Dynamic Pricing with Demand Learning](https://mlsanity.com/paper/2311.16528/) (2023)
- [Differential Privacy via Distributionally Robust Optimization](https://mlsanity.com/paper/2304.12681/) (2023)
- [On the Optimal Regret of Locally Private Linear Contextual Bandit](https://mlsanity.com/paper/2404.09413/) (2024)
- [On Private Online Convex Optimization: Optimal Algorithms in ℓp-Geometry and High Dimensional Contextual Bandits](https://mlsanity.com/paper/2206.08111/) (2022)
- [Majority Vote for Distributed Differentially Private Sign Selection](https://mlsanity.com/paper/2209.04419/) (2022)
- [Privacy Preserving Adaptive Experiment Design](https://mlsanity.com/paper/2401.08224/) (2024)
- [Private Optimal Inventory Policy Learning for Feature-based Newsvendor with Unknown Demand](https://mlsanity.com/paper/2404.15466/) (2024)
- [Locally Private Nonparametric Contextual Multi-armed Bandits](https://mlsanity.com/paper/2503.08098/) (2025)
- [Beyond ATE: Multi-Criteria Design for A/B Testing](https://mlsanity.com/paper/2509.05864/) (2025)
- [On Non-Stationary Dynamic Pricing: Adaptivity and Optimality](https://mlsanity.com/paper/2607.24115/) (2026)

## Abstract (arXiv)

In the recent decades, the advance of information technology and abundant personal data facilitate the application of algorithmic personalized pricing. However, this leads to the growing concern of potential violation of privacy due to adversarial attack. To address the privacy issue, this paper studies a dynamic personalized pricing problem with textitunknown nonparametric demand models under data privacy protection. Two concepts of data privacy, which have been widely applied in practices, are introduced: textitcentral differential privacy (CDP) and textitlocal differential privacy (LDP), which is proved to be stronger than CDP in many cases. We develop two algorithms which make pricing decisions and learn the unknown demand on the fly, while satisfying the CDP and LDP gurantees respectively. In particular, for the algorithm with CDP guarantee, the regret is proved to be at most tilde O(T(d+2)/(d+4)+varepsilon-1Td/(d+4)). Here, the parameter T denotes the length of the time horizon, d is the dimension of the personalized information vector, and the key parameter varepsilon>0 measures the strength of privacy (smaller varepsilon indicates a stronger privacy protection). On the other hand, for the algorithm with LDP guarantee, its regret is proved to be at most tilde O(varepsilon-2/(d+2)T(d+1)/(d+2)), which is near-optimal as we prove a lower bound of Omega(varepsilon-2/(d+2)T(d+1)/(d+2)) for any algorithm with LDP guarantee.