Vovk, Vladimir (2006) Metric entropy in competitive on-line prediction.
Full text access: Open
Competitive on-line prediction (also known as universal prediction of individual sequences) is a strand of learning theory avoiding making anystochastic assumptions about the way the observations are generated. The predictor's goal is to compete with a benchmark class of prediction rules, which is often a proper Banach function space. Metric entropy provides a unifying framework for competitive on-line prediction: the numerous known upper bounds on the metric entropy of various compact sets in function spaces readily imply bounds on the performance of on-line prediction strategies. This paper discusses strengths and limitations of the direct approach to competitive on-line prediction via metric entropy, including comparisons to other approaches.
This is a Submitted version This version's date is: 9/9/2006 This item is not peer reviewed
https://repository.royalholloway.ac.uk/items/6deab548-e42b-7102-6250-4be9064bbefc/2/
Deposited by Research Information System (atira) on 24-Jul-2012 in Royal Holloway Research Online.Last modified on 24-Jul-2012
41 pages