# Differentially Private Online Item Pricing

arXiv: https://arxiv.org/abs/2305.11362 · HTML: https://mlsanity.com/paper/2305.11362/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 37 references that are in the map.
- First posted on arXiv 19 May 2023.

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

- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [The Sample Complexity of Revenue Maximization](https://mlsanity.com/paper/1502.00963/) (2015)
- [Learning Prices for Repeated Auctions with Strategic Buyers](https://mlsanity.com/paper/1311.6838/) (2013)
- [Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization](https://mlsanity.com/paper/1711.03091/) (2017)
- [Oracle-Efficient Online Learning and Auction Design](https://mlsanity.com/paper/1611.01688/) (2016)
- [Private Matchings and Allocations](https://mlsanity.com/paper/1311.2828/) (2013)
- [Revenue Maximization for Query Pricing](https://mlsanity.com/paper/1909.00845/) (2019)
- [Learning Optimal Reserve Price against Non-myopic Bidders](https://mlsanity.com/paper/1804.11060/) (2018)
- [Multi-scale Online Learning and its Applications to Online Auctions](https://mlsanity.com/paper/1705.09700/) (2017)
- [The Design of Arbitrage-Free Data Pricing Schemes](https://mlsanity.com/paper/1606.09376/) (2016)
- [Optimal, Truthful, and Private Securities Lending](https://mlsanity.com/paper/1912.06202/) (2019)

## Abstract (arXiv)

This work addresses the problem of revenue maximization in a repeated, unlimited supply item-pricing auction while preserving buyer privacy. We present a novel algorithm that provides differential privacy with respect to the buyer's input pair: item selection and bid. Notably, our algorithm is the first to offer a sublinear O(√TlogT) regret with a privacy guarantee. Our method is based on an exponential weights meta-algorithm, and we mitigate the issue of discontinuities in revenue functions via small random perturbations. As a result of its structural similarity to the exponential mechanism, our method inherently secures differential privacy. We also extend our algorithm to accommodate scenarios where buyers strategically bid over successive rounds. The inherent differential privacy allows us to adapt our algorithm with minimal modification to ensure a sublinear regret in this setting.