The Price is (Probably) Right: Learning Market Equilibria from Samples

12/29/2020
by   Omer Lev, et al.
0

Equilibrium computation in markets usually considers settings where player valuation functions are known. We consider the setting where player valuations are unknown; using a PAC learning-theoretic framework, we analyze some classes of common valuation functions, and provide algorithms which output direct PAC equilibrium allocations, not estimates based on attempting to learn valuation functions. Since there exist trivial PAC market outcomes with an unbounded worst-case efficiency loss, we lower-bound the efficiency of our algorithms. While the efficiency loss under general distributions is rather high, we show that in some cases (e.g., unit-demand valuations), it is possible to find a PAC market equilibrium with significantly better utility.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/20/2022

PAC-Bayesian Learning of Optimization Algorithms

We apply the PAC-Bayes theory to the setting of learning-to-optimize. To...
research
02/21/2020

Common knowledge equilibrium of separable securities in distributed information market

We investigate common knowledge equilibrium of separable securities in d...
research
03/20/2019

A Learning Framework for Distribution-Based Game-Theoretic Solution Concepts

The past few years have seen several works establishing PAC frameworks f...
research
06/12/2020

PAC-Bayes unleashed: generalisation bounds with unbounded losses

We present new PAC-Bayesian generalisation bounds for learning problems ...
research
07/30/2014

Market Making with Decreasing Utility for Information

We study information elicitation in cost-function-based combinatorial pr...
research
10/07/2022

PAC Security: Automatic Privacy Measurement and Control of Data Processing

We propose and study a new privacy definition, termed Probably Approxima...
research
11/12/2018

Forming Probably Stable Communities with Limited Interactions

A community needs to be partitioned into disjoint groups; each community...

Please sign up or login with your details

Forgot password? Click here to reset