Learning Competitive Equilibria in Noisy Combinatorial Markets

TL;DR

This paper introduces a robust learning framework for estimating competitive equilibria in noisy combinatorial markets, providing algorithms with finite-sample guarantees that outperform baseline methods in efficiency.

Contribution

It develops two algorithms for learning CE under valuation noise, including an adaptive pruning method that reduces sample complexity while maintaining accuracy.

Findings

The pruning algorithm achieves better estimates with fewer samples.

The algorithms provide finite-sample guarantees for CE approximation.

Experimental results show the pruning method outperforms the baseline.

Abstract

We present a methodology to robustly estimate the competitive equilibria (CE) of combinatorial markets under the assumption that buyers do not know their precise valuations for bundles of goods, but instead can only provide noisy estimates. We first show tight lower- and upper-bounds on the buyers' utility loss, and hence the set of CE, given a uniform approximation of one market by another. We then develop a learning framework for our setup, and present two probably-approximately-correct algorithms for learning CE, i.e., producing uniform approximations that preserve CE, with finite-sample guarantees. The first is a baseline that uses Hoeffding's inequality to produce a uniform approximation of buyers' valuations with high probability. The second leverages a connection between the first welfare theorem of economics and uniform approximations to adaptively prune value queries when it determines that they are provably not part of a CE. We experiment with our algorithms and find that the pruning algorithm achieves better estimates than the baseline with far fewer samples.