# Learning Competitive Equilibria in Exchange Economies with Bandit Feedback

arXiv: https://arxiv.org/abs/2106.06616 · HTML: https://mlsanity.com/paper/2106.06616/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 55 references that are in the map.
- First posted on arXiv 11 Jun 2021.

## Builds on (most cited first, 6 of 6)

- [Provably Optimal Algorithms for Generalized Linear Contextual Bandits](https://mlsanity.com/paper/1703.00048/) (2017)
- [Oracle-Efficient Online Learning and Auction Design](https://mlsanity.com/paper/1611.01688/) (2016)
- [Sample Complexity of Automated Mechanism Design](https://mlsanity.com/paper/1606.04145/) (2016)
- [Online Learning Demands in Max-min Fairness](https://mlsanity.com/paper/2012.08648/) (2020)
- [Multi-parameter Mechanisms with Implicit Payment Computation](https://mlsanity.com/paper/1302.4138/) (2013)
- [Competitive Equilibrium with Indivisible Goods and Generic Budgets](https://mlsanity.com/paper/1703.08150/) (2017)

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

- [Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces](https://mlsanity.com/paper/2306.10606/) (2023)
- [Learning Classifiers That Induce Markets](https://mlsanity.com/paper/2502.20012/) (2025)

## Abstract (arXiv)

The sharing of scarce resources among multiple rational agents is one of the classical problems in economics. In exchange economies, which are used to model such situations, agents begin with an initial endowment of resources and exchange them in a way that is mutually beneficial until they reach a competitive equilibrium (CE). The allocations at a CE are Pareto efficient and fair. Consequently, they are used widely in designing mechanisms for fair division. However, computing CEs requires the knowledge of agent preferences which are unknown in several applications of interest. In this work, we explore a new online learning mechanism, which, on each round, allocates resources to the agents and collects stochastic feedback on their experience in using that allocation. Its goal is to learn the agent utilities via this feedback and imitate the allocations at a CE in the long run. We quantify CE behavior via two losses and propose a randomized algorithm which achieves sublinear loss under a parametric class of utilities. Empirically, we demonstrate the effectiveness of this mechanism through numerical simulations.