Optimal regret minimization in posted-price auctions with strategic buyers

Mehryar Mohri, Andres Muñoz Medina

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We study revenue optimization learning algorithms for posted-price auctions with strategic buyers. We analyze a very broad family of monotone regret minimization algorithms for this problem, which includes the previously best known algorithm, and show that no algorithm in that family admits a strategic regret more favorable than Ω(√T). We then introduce a new algorithm that achieves a strategic regret differing from the lower bound only by a factor in O(logT), an exponential improvement upon the previous best algorithm. Our new algorithm admits a natural analysis and simpler proofs, and the ideas behind its design are general. We also report the results of empirical evaluations comparing our algorithm with the previous state of the art and show a consistent exponential improvement in several different scenarios.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
Pages1871-1879
Number of pages9
Volume3
EditionJanuary
StatePublished - 2014
Event28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 - Montreal, Canada
Duration: Dec 8 2014Dec 13 2014

Other

Other28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014
CountryCanada
CityMontreal
Period12/8/1412/13/14

Fingerprint

Learning algorithms

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Mohri, M., & Medina, A. M. (2014). Optimal regret minimization in posted-price auctions with strategic buyers. In Advances in Neural Information Processing Systems (January ed., Vol. 3, pp. 1871-1879). Neural information processing systems foundation.

Optimal regret minimization in posted-price auctions with strategic buyers. / Mohri, Mehryar; Medina, Andres Muñoz.

Advances in Neural Information Processing Systems. Vol. 3 January. ed. Neural information processing systems foundation, 2014. p. 1871-1879.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mohri, M & Medina, AM 2014, Optimal regret minimization in posted-price auctions with strategic buyers. in Advances in Neural Information Processing Systems. January edn, vol. 3, Neural information processing systems foundation, pp. 1871-1879, 28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014, Montreal, Canada, 12/8/14.
Mohri M, Medina AM. Optimal regret minimization in posted-price auctions with strategic buyers. In Advances in Neural Information Processing Systems. January ed. Vol. 3. Neural information processing systems foundation. 2014. p. 1871-1879
Mohri, Mehryar ; Medina, Andres Muñoz. / Optimal regret minimization in posted-price auctions with strategic buyers. Advances in Neural Information Processing Systems. Vol. 3 January. ed. Neural information processing systems foundation, 2014. pp. 1871-1879
@inproceedings{0e64ba151589460bac4fa80dd5690086,
title = "Optimal regret minimization in posted-price auctions with strategic buyers",
abstract = "We study revenue optimization learning algorithms for posted-price auctions with strategic buyers. We analyze a very broad family of monotone regret minimization algorithms for this problem, which includes the previously best known algorithm, and show that no algorithm in that family admits a strategic regret more favorable than Ω(√T). We then introduce a new algorithm that achieves a strategic regret differing from the lower bound only by a factor in O(logT), an exponential improvement upon the previous best algorithm. Our new algorithm admits a natural analysis and simpler proofs, and the ideas behind its design are general. We also report the results of empirical evaluations comparing our algorithm with the previous state of the art and show a consistent exponential improvement in several different scenarios.",
author = "Mehryar Mohri and Medina, {Andres Mu{\~n}oz}",
year = "2014",
language = "English (US)",
volume = "3",
pages = "1871--1879",
booktitle = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",
edition = "January",

}

TY - GEN

T1 - Optimal regret minimization in posted-price auctions with strategic buyers

AU - Mohri, Mehryar

AU - Medina, Andres Muñoz

PY - 2014

Y1 - 2014

N2 - We study revenue optimization learning algorithms for posted-price auctions with strategic buyers. We analyze a very broad family of monotone regret minimization algorithms for this problem, which includes the previously best known algorithm, and show that no algorithm in that family admits a strategic regret more favorable than Ω(√T). We then introduce a new algorithm that achieves a strategic regret differing from the lower bound only by a factor in O(logT), an exponential improvement upon the previous best algorithm. Our new algorithm admits a natural analysis and simpler proofs, and the ideas behind its design are general. We also report the results of empirical evaluations comparing our algorithm with the previous state of the art and show a consistent exponential improvement in several different scenarios.

AB - We study revenue optimization learning algorithms for posted-price auctions with strategic buyers. We analyze a very broad family of monotone regret minimization algorithms for this problem, which includes the previously best known algorithm, and show that no algorithm in that family admits a strategic regret more favorable than Ω(√T). We then introduce a new algorithm that achieves a strategic regret differing from the lower bound only by a factor in O(logT), an exponential improvement upon the previous best algorithm. Our new algorithm admits a natural analysis and simpler proofs, and the ideas behind its design are general. We also report the results of empirical evaluations comparing our algorithm with the previous state of the art and show a consistent exponential improvement in several different scenarios.

UR - http://www.scopus.com/inward/record.url?scp=84937922049&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937922049&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84937922049

VL - 3

SP - 1871

EP - 1879

BT - Advances in Neural Information Processing Systems

PB - Neural information processing systems foundation

ER -