# Recommender Systems meet Mechanism Design

arXiv: https://arxiv.org/abs/2110.12558 · HTML: https://mlsanity.com/paper/2110.12558/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 49 references that are in the map.
- First posted on arXiv 25 Oct 2021.

## Builds on (most cited first, 19 of 19)

- [Automated Mechanism Design via Neural Networks](https://mlsanity.com/paper/1805.03382/) (2018)
- [Learning Simple Auctions](https://mlsanity.com/paper/1604.03171/) (2016)
- [Multi-Item Mechanisms without Item-Independence: Learnability via Robustness](https://mlsanity.com/paper/1911.02146/) (2019)
- [Learning Multi-item Auctions with (or without) Samples](https://mlsanity.com/paper/1709.00228/) (2017)
- [Strong Duality for a Multiple-Good Monopolist](https://mlsanity.com/paper/1409.4150/) (2014)
- [The Sample Complexity of Up-to-varepsilon Multi-Dimensional Revenue Maximization](https://mlsanity.com/paper/1808.02458/) (2018)
- [Duality and Optimality of Auctions for Uniform Distributions](https://mlsanity.com/paper/1404.2329/) (2014)
- [A Sample Complexity Measure with Applications to Learning Optimal Auctions](https://mlsanity.com/paper/1704.02598/) (2017)
- [Understanding Incentives: Mechanism Design becomes Algorithm Design](https://mlsanity.com/paper/1305.4002/) (2013)
- [A Simple and Approximately Optimal Mechanism for an Additive Buyer](https://mlsanity.com/paper/1405.6146/) (2014)
- [A Duality-Based Unified Approach to Bayesian Mechanism Design](https://mlsanity.com/paper/1812.01577/) (2018)
- [Sampling and Representation Complexity of Revenue Maximization](https://mlsanity.com/paper/1402.4535/) (2014)
- [An n-to-1 Bidder Reduction for Multi-item Auctions and its Applications](https://mlsanity.com/paper/1406.3278/) (2014)
- [Optimal Auctions with Restricted Allocations](https://mlsanity.com/paper/1606.01610/) (2016)
- [Mechanism Design via Optimal Transport](https://mlsanity.com/paper/1503.01958/) (2015)
- [Simple Mechanisms for Subadditive Buyers via Duality](https://mlsanity.com/paper/1611.06910/) (2016)
- [The Menu-Size Complexity of Revenue Approximation](https://mlsanity.com/paper/1604.06580/) (2016)
- [Reducing Revenue to Welfare Maximization: Approximation Algorithms and other Generalizations](https://mlsanity.com/paper/1305.4000/) (2013)
- [Mechanism Design for Subadditive Agents via an Ex-Ante Relaxation](https://mlsanity.com/paper/1603.03806/) (2016)

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

- [A Robust Multi-Item Auction Design with Statistical Learning](https://mlsanity.com/paper/2302.00941/) (2023)
- [Refined Mechanism Design for Approximately Structured Priors via Active Regression](https://mlsanity.com/paper/2310.07874/) (2023)

## Abstract (arXiv)

Machine learning has developed a variety of tools for learning and representing high-dimensional distributions with structure. Recent years have also seen big advances in designing multi-item mechanisms. Akin to overfitting, however, these mechanisms can be extremely sensitive to the Bayesian prior that they target, which becomes problematic when that prior is only approximately known. At the same time, even if access to the exact Bayesian prior is given, it is known that optimal or even approximately optimal multi-item mechanisms run into sample, computational, representation and communication intractability barriers. We consider a natural class of multi-item mechanism design problems with very large numbers of items, but where the bidders' value distributions can be well-approximated by a topic model akin to those used in recommendation systems with very large numbers of possible recommendations. We propose a mechanism design framework for this setting, building on a recent robustification framework by Brustle et al., which disentangles the statistical challenge of estimating a multi-dimensional prior from the task of designing a good mechanism for it, and robustifies the performance of the latter against the estimation error of the former. We provide an extension of this framework appropriate for our setting, which allows us to exploit the expressive power of topic models to reduce the effective dimensionality of the mechanism design problem and remove the dependence of its computational, communication and representation complexity on the number of items.