Efficiency Guarantees from Data
Darrell Hoy, Denis Nekipelov, Vasilis Syrgkanis

TL;DR
This paper introduces a data-dependent measure of efficiency in game-theoretic outcomes, specifically in auctions, which improves upon traditional worst-case bounds by leveraging observed strategic behavior.
Contribution
It proposes a novel data-dependent framework for bounding efficiency in auctions that is robust to errors and does not require inferring private information.
Findings
Empirical bounds on auction efficiency are significantly tighter than worst-case bounds.
The approach is robust to statistical errors and model mis-specification.
Application to real auction data demonstrates practical effectiveness.
Abstract
Analysis of efficiency of outcomes in game theoretic settings has been a main item of study at the intersection of economics and computer science. The notion of the price of anarchy takes a worst-case stance to efficiency analysis, considering instance independent guarantees of efficiency. We propose a data-dependent analog of the price of anarchy that refines this worst-case assuming access to samples of strategic behavior. We focus on auction settings, where the latter is non-trivial due to the private information held by participants. Our approach to bounding the efficiency from data is robust to statistical errors and mis-specification. Unlike traditional econometrics, which seek to learn the private information of players from observed behavior and then analyze properties of the outcome, we directly quantify the inefficiency without going through the private information. We apply…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAuction Theory and Applications · Consumer Market Behavior and Pricing · Advanced Bandit Algorithms Research
