Complexity-Based Approach to Calibration With Checking Rules

Loading...
Thumbnail Image
Penn collection
Statistics Papers
Degree type
Discipline
Subject
Statistics and Probability
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Foster, Dean P
Rakhlin, Alexander
Sridharan, Karthik
Tewari, Ambuj
Contributor
Abstract

We 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.

Advisor
Date of presentation
2011-01-01
Conference name
Statistics Papers
Conference dates
2023-05-17T15:26:36.000
Conference location
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Recommended citation
Collection