File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
  • Find via Find It@HKUL
Supplementary

Conference Paper: Learning Optimal Reserve Price against Non-myopic Bidders

TitleLearning Optimal Reserve Price against Non-myopic Bidders
Authors
Issue Date2018
PublisherNeural Information Processing Systems Foundation, Inc. The Proceedings' web site is located at https://papers.nips.cc/
Citation
Thirty-second Conference on Neural Information Processing Systems, Montréal, Canada, 3-8 December 2018. In Bengio, S ... et al (eds.), Advances in Neural Information Processing Systems 31 (NIPS 2018 Proceedings) How to Cite?
AbstractWe consider the problem of learning optimal reserve price in repeated auctions against non-myopic bidders, who may bid strategically in order to gain in future rounds even if the single-round auctions are truthful. Previous algorithms, e.g., empirical pricing, do not provide non-trivial regret rounds in this setting in general. We introduce algorithms that obtain small regret against non-myopic bidders either when the market is large, i.e., no bidder appears in a constant fraction of the rounds, or when the bidders are impatient, i.e., they discount future utility by some factor mildly bounded away from one. Our approach carefully controls what information is revealed to each bidder, and builds on techniques from differentially private online learning as well as the recent line of works on jointly differentially private algorithms.
DescriptionPoster Session A
Persistent Identifierhttp://hdl.handle.net/10722/273021
ISSN

 

DC FieldValueLanguage
dc.contributor.authorHuang, Z-
dc.contributor.authorLiu, J-
dc.contributor.authorWang, X-
dc.date.accessioned2019-08-06T09:21:03Z-
dc.date.available2019-08-06T09:21:03Z-
dc.date.issued2018-
dc.identifier.citationThirty-second Conference on Neural Information Processing Systems, Montréal, Canada, 3-8 December 2018. In Bengio, S ... et al (eds.), Advances in Neural Information Processing Systems 31 (NIPS 2018 Proceedings)-
dc.identifier.issn1049-5258-
dc.identifier.urihttp://hdl.handle.net/10722/273021-
dc.descriptionPoster Session A-
dc.description.abstractWe consider the problem of learning optimal reserve price in repeated auctions against non-myopic bidders, who may bid strategically in order to gain in future rounds even if the single-round auctions are truthful. Previous algorithms, e.g., empirical pricing, do not provide non-trivial regret rounds in this setting in general. We introduce algorithms that obtain small regret against non-myopic bidders either when the market is large, i.e., no bidder appears in a constant fraction of the rounds, or when the bidders are impatient, i.e., they discount future utility by some factor mildly bounded away from one. Our approach carefully controls what information is revealed to each bidder, and builds on techniques from differentially private online learning as well as the recent line of works on jointly differentially private algorithms.-
dc.languageeng-
dc.publisherNeural Information Processing Systems Foundation, Inc. The Proceedings' web site is located at https://papers.nips.cc/-
dc.relation.ispartofAdvances in Neural Information Processing Systems (NIPS)-
dc.relation.ispartof32nd Conference on Neural Information Processing Systems (NIPS 2018)-
dc.titleLearning Optimal Reserve Price against Non-myopic Bidders-
dc.typeConference_Paper-
dc.identifier.emailHuang, Z: zhiyi@cs.hku.hk-
dc.identifier.authorityHuang, Z=rp01804-
dc.identifier.hkuros300035-
dc.identifier.volume31-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats