Learning Simple Auctions

TL;DR

This paper introduces a framework for efficiently learning near-optimal simple auctions from samples, applicable to various auction types, by analyzing the structure of allocation rules and revenue functions.

Contribution

It provides a unified approach to bound sample complexity for learning simple auctions, covering many auction classes and enabling learning with unknown priors.

Findings

Polynomial sample complexity bounds for learning simple auctions.

Framework applies to anonymous and non-anonymous, single and multiple buyer auctions.

Enables learning near-optimal auctions with unknown priors from polynomially many samples.

Abstract

We present a general framework for proving polynomial sample complexity bounds for the problem of learning from samples the best auction in a class of "simple" auctions. Our framework captures all of the most prominent examples of "simple" auctions, including anonymous and non-anonymous item and bundle pricings, with either a single or multiple buyers. The technique we propose is to break the analysis of auctions into two natural pieces. First, one shows that the set of allocation rules have large amounts of structure; second, fixing an allocation on a sample, one shows that the set of auctions agreeing with this allocation on that sample have revenue functions with low dimensionality. Our results effectively imply that whenever it's possible to compute a near-optimal simple auction with a known prior, it is also possible to compute such an auction with an unknown prior (given a polynomial number of samples).