Sangam: A Confluence of Knowledge Streams

Dynamic Incentive-Aware Learning: Robust Pricing in Contextual Auctions

Show simple item record

dc.creator Golrezaei, Negin
dc.creator Javanmard, Adel
dc.creator Mirrokni, Vahab
dc.date 2021-10-27T20:04:36Z
dc.date 2021-10-27T20:04:36Z
dc.date 2021
dc.date 2021-04-08T15:11:20Z
dc.date.accessioned 2023-03-01T18:09:50Z
dc.date.available 2023-03-01T18:09:50Z
dc.identifier https://hdl.handle.net/1721.1/134361
dc.identifier.uri http://localhost:8080/xmlui/handle/CUHPOERS/278991
dc.description © 2020 INFORMS Motivated by pricing in ad exchange markets, we consider the problem of robust learning of reserve prices against strategic buyers in repeated contextual second-price auctions. Buyers’ valuations for an item depend on the context that describes the item. However, the seller is not aware of the relationship between the context and buyers’ valuations (i.e., buyers’ preferences). The seller’s goal is to design a learning policy to set reserve prices via observing the past sales data, and her objective is to minimize her regret for revenue, where the regret is computed against a clairvoyant policy that knows buyers’ heterogeneous preferences. Given the seller’s goal, utility-maximizing buyers have the incentive to bid untruthfully in order to manipulate the seller’s learning policy. We propose learning policies that are robust to such strategic behavior. These policies use the outcomes of the auctions, rather than the submitted bids, to estimate the preferences while controlling the long-term effect of the outcome of each auction on the future reserve prices. When the market noise distribution is known to the seller, we propose a policy called contextual robust pricing that achieves a T-period regret of O(d log(T d) log(T)), where d is the dimension of the contextual information. When the market noise distribution is unknown to the seller, we propose two policies whose regrets are sublinear in T.
dc.format application/pdf
dc.language en
dc.publisher Institute for Operations Research and the Management Sciences (INFORMS)
dc.relation 10.1287/OPRE.2020.1991
dc.relation Operations Research
dc.rights Creative Commons Attribution-Noncommercial-Share Alike
dc.rights http://creativecommons.org/licenses/by-nc-sa/4.0/
dc.source arXiv
dc.title Dynamic Incentive-Aware Learning: Robust Pricing in Contextual Auctions
dc.type Article
dc.type http://purl.org/eprint/type/JournalArticle


Files in this item

Files Size Format View
2002.11137.pdf 1.046Mb application/pdf View/Open

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse