Average-case approximation ratio of scheduling without payments

Research output: Chapter in Book/Report/Conference proceedingChapter in a published conference proceeding

2 Citations (SciVal)

Abstract

Apart from the principles and methodologies inherited from Economics and Game Theory, the studies in Algorithmic Mechanism Design typically employ the worst-case analysis and approximation schemes of Theoretical Computer Science. For instance, the approximation ratio, which is the canonical measure of evaluating how well an incentive-compatible mechanism approximately optimizes the objective, is defined in the worst-case sense. It compares the performance of the optimal mechanism against the performance of a truthful mechanism, for all possible inputs. In this paper, we take the average-case analysis approach, and tackle one of the primary motivating problems in Algorithmic Mechanism Design -- the scheduling problem [Nisan and Ronen 1999]. One version of this problem which includes a verification component is studied by [Koutsoupias 2014]. It was shown that the problem has a tight approximation ratio bound of (n+1)/2 for the single-task setting, where n is the number of machines. We show, however, when the costs of the machines to executing the task follow any independent and identical distribution, the average-case approximation ratio of the mechanism given in [Koutsoupias 2014] is upper bounded by a constant. This positive result asymptotically separates the average-case ratio from the worst-case ratio, and indicates that the optimal mechanism for the problem actually works well on average, although in the worst-case the expected cost of the mechanism is Theta(n) times that of the optimal cost.
Original languageEnglish
Title of host publicationThe Thirty-Second AAAI Conference on Artificial Intelligence
PublisherAAAI
Pages1298-1304
Number of pages7
Publication statusPublished - 7 Feb 2018

Fingerprint

Dive into the research topics of 'Average-case approximation ratio of scheduling without payments'. Together they form a unique fingerprint.

Cite this