File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1145/3033274.3085145
- Scopus: eid_2-s2.0-85025802830
- WOS: WOS:000628648900049
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Online Auctions and Multi-scale Online Learning
Title | Online Auctions and Multi-scale Online Learning |
---|---|
Authors | |
Issue Date | 2017 |
Publisher | ACM Press. |
Citation | ACM Conference on Economics and Computation (EC '17), Cambridge, MA, 26-30 June 2017, p. 497-514 How to Cite? |
Abstract | We consider revenue maximization in online auctions and pricing. A seller sells an identical item in each period to a new buyer, or a new set of buyers. For the online posted pricing problem, we show regret bounds that scale with the best fixed price, rather than the range of the values. We also show regret bounds that are almost scale free, and match the offline sample complexity, when comparing to a benchmark that requires a lower bound on the market share. These results are obtained by generalizing the classical learning from experts and multi-armed bandit problems to their multi-scale versions. In this version, the reward of each action is in a different range, and the regret w.r.t. a given action scales with its own range, rather than the maximum range. |
Persistent Identifier | http://hdl.handle.net/10722/246609 |
ISBN | |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Bubeck, S | - |
dc.contributor.author | Devanur, NR | - |
dc.contributor.author | Huang, Z | - |
dc.contributor.author | Niazadeh, R | - |
dc.date.accessioned | 2017-09-18T02:31:30Z | - |
dc.date.available | 2017-09-18T02:31:30Z | - |
dc.date.issued | 2017 | - |
dc.identifier.citation | ACM Conference on Economics and Computation (EC '17), Cambridge, MA, 26-30 June 2017, p. 497-514 | - |
dc.identifier.isbn | 978-1-4503-4527-9 | - |
dc.identifier.uri | http://hdl.handle.net/10722/246609 | - |
dc.description.abstract | We consider revenue maximization in online auctions and pricing. A seller sells an identical item in each period to a new buyer, or a new set of buyers. For the online posted pricing problem, we show regret bounds that scale with the best fixed price, rather than the range of the values. We also show regret bounds that are almost scale free, and match the offline sample complexity, when comparing to a benchmark that requires a lower bound on the market share. These results are obtained by generalizing the classical learning from experts and multi-armed bandit problems to their multi-scale versions. In this version, the reward of each action is in a different range, and the regret w.r.t. a given action scales with its own range, rather than the maximum range. | - |
dc.language | eng | - |
dc.publisher | ACM Press. | - |
dc.relation.ispartof | Proceedings of the 2017 ACM Conference on Economics and Computation, EC '17 | - |
dc.title | Online Auctions and Multi-scale Online Learning | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Huang, Z: zhiyi@cs.hku.hk | - |
dc.identifier.authority | Huang, Z=rp01804 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1145/3033274.3085145 | - |
dc.identifier.scopus | eid_2-s2.0-85025802830 | - |
dc.identifier.hkuros | 276914 | - |
dc.identifier.spage | 497 | - |
dc.identifier.epage | 514 | - |
dc.identifier.isi | WOS:000628648900049 | - |
dc.publisher.place | New York, NY | - |