vix.ing · top · new · best · stats · spec

Knightian Robustness from Regret Minimization

2014/03/25 by Alessandro Chiesa, Silvio Micali, Chiesa, Alessandro +3
Computer Science · Decision Sciences · #Auction Theory and Applications #Machine Learning and Algorithms #Machine Learning and Data Classification #cs.GT

paper · pdf · doi:10.48550/arxiv.1403.6409

arxiv created 2014/04/01 · arxiv updated 2014/04/02

Abstract

We consider auctions in which the players have very limited knowledge about their own valuations. Specifically, the only information that a Knightian player i has about the profile of true valuations, θ^*, consists of a set of distributions, from one of which θi^* has been drawn. We analyze the social-welfare performance of the VCG mechanism, for unrestricted combinatorial auctions, when Knightian players that either (a) choose a regret-minimizing strategy, or (b) resort to regret minimization only to refine further their own sets of undominated strategies, if needed. We prove that this performance is very good.

Related