Complexity-Based Approach to Calibration With Checking Rules

Simple item page
dc.contributor.authorFoster, Dean P
dc.contributor.authorRakhlin, Alexander
dc.contributor.authorSridharan, Karthik
dc.contributor.authorTewari, Ambuj
dc.date2023-05-17T15:26:36.000
dc.date.accessioned2023-05-23T03:33:59Z
dc.date.available2023-05-23T03:33:59Z
dc.date.issued2011-01-01
dc.date.submitted2016-08-19T10:43:46-07:00
dc.description.abstractWe consider the problem of forecasting a sequence of outcomes from an unknown source. The quality of the forecaster is measured by a family of checking rules. We prove upper bounds on the value of the associated game, thus certifying the existence of a calibrated strategy for the forecaster. We show that complexity of the family of checking rules can be captured by the notion of a sequential cover introduced in [19]. Various natural assumptions on the class of checking rules are considered, including finiteness of Vapnik-Chervonenkis and Littlestone's dimensions.
dc.identifier.urihttps://repository.upenn.edu/handle/20.500.14332/47495
dc.legacy.articleid1461
dc.legacy.fulltexturlhttps://repository.upenn.edu/cgi/viewcontent.cgi?article=1461&context=statistics_papers&unstamped=1
dc.source.beginpage293
dc.source.endpage314
dc.source.issue141
dc.source.journalStatistics Papers
dc.source.journaltitleJMLR: Workshop and Conference Proceedings
dc.source.peerreviewedtrue
dc.source.statuspublished
dc.source.volume19
dc.subject.otherStatistics and Probability
dc.titleComplexity-Based Approach to Calibration With Checking Rules
dc.typePresentation
digcom.contributor.authorFoster, Dean P
digcom.contributor.authorRakhlin, Alexander
digcom.contributor.authorSridharan, Karthik
digcom.contributor.authorTewari, Ambuj
digcom.identifierstatistics_papers/141
digcom.identifier.contextkey9004595
digcom.identifier.submissionpathstatistics_papers/141
digcom.typeconference
dspace.entity.typePublication
upenn.schoolDepartmentCenterStatistics Papers
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Complexity_based_approach_to_calibration_1.pdf
Size:
213.63 KB
Format:
Adobe Portable Document Format
Download
Collection
Presentations