完整後設資料紀錄
DC 欄位語言
dc.contributor.authorLee, Chia-Jungen_US
dc.contributor.authorTsai, Shi-Chunen_US
dc.contributor.authorYang, Ming-Chuanen_US
dc.date.accessioned2014-12-08T15:36:53Z-
dc.date.available2014-12-08T15:36:53Z-
dc.date.issued2014-01-01en_US
dc.identifier.isbn978-3-319-08783-2; 978-3-319-08782-5en_US
dc.identifier.issn0302-9743en_US
dc.identifier.urihttp://hdl.handle.net/11536/25276-
dc.description.abstractWe study the prediction with expert advice problem, where in each round, the player selects one of N actions and incurs the corresponding loss according to an N-dimensional linear loss vector, and aim to minimize the regret. In this paper, we consider a new measure of the loss functions, which we call L-infinity-variation. Consider the loss functions with small L-infinity-variation, if the player is allowed to have some information related to the variation in each round, we can obtain an online bandit algorithm for the problem without using the self-concordance methodology, which conditionally answers an open problem in [8]. Another related problem is the combinatorial prediction game, in which the set of actions is a subset of {0, 1}(d), and the loss function is in [-1, 1](d). We provide an online algorithm in the semi-bandit setting when the loss functions have small L-infinity-variation.en_US
dc.language.isoen_USen_US
dc.titleOnline Prediction Problems with Variationen_US
dc.typeProceedings Paperen_US
dc.identifier.journalCOMPUTING AND COMBINATORICS, COCOON 2014en_US
dc.citation.volume8591en_US
dc.citation.issueen_US
dc.citation.spage49en_US
dc.citation.epage60en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000343883800005-
顯示於類別:會議論文