Paper Info
Title
Prequential Plug-In Codes That Achieve Optimal Redundancy Rates Even If The Model Is Wrong
Abstract
We analyse the prequential plug-in codes relative to one-parameter exponential families M. We show that if data are sampled i.i.d. from some distribution outside M, then the redundancy of any plug-in prequential code grows at rate larger than 1/2 ln n in the worst case. This means that plug-in codes, such as the Rissanen-Dawid ML code, may behave inferior to other important universal codes such as the 2-part MDL, Shtarkov and Bayes codes, for which the redundancy is always 1/2 ln n + O(1). However, we also show that a slight modification of the ML plug-in code, "almost" in the model, does achieve the optimal redundancy even if the the true distribution is outside M.
Year
DOI
Venue
2010
10.1109/ISIT.2010.5513591
2010 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY
Keywords
DocType
Volume
computational modeling,mathematics,codes,zinc,information theory,maximum likelihood estimation,computer science,maximum likelihood estimator,gaussian distribution,mathematical model,parametric statistics,redundancy,linear regression,data compression,bayesian methods
Conference
abs/1002.0757
Citations 
PageRank 
References 
0
0.34
0
Authors
2
Name
Order
Citations
PageRank
Peter Grünwald100.34
Wojciech Kotlowski215816.32