16 citations · 58 across the 10 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2008★ 10 cited
Combining Expert Advice Efficiently
Wouter Koolen, Steven de Rooij
We show how models for prediction with expert advice can be defined concisely and clearly using hidden Markov models (HMMs); standard HMM algorithms can then be used to efficiently…
cs.LG2005
Asymptotic Log-loss of Prequential Maximum Likelihood Codes
Peter Grunwald, Steven de Rooij
We analyze the Dawid-Rissanen prequential maximum likelihood codes relative to one-parameter exponential family models M. If data are i.i.d. according to an (essentially) arbitrary…
cs.LG2005★ 2 cited
An Empirical Study of MDL Model Selection with Infinite Parametric Complexity
Steven de Rooij, Peter Grunwald
Parametric complexity is a central concept in MDL model selection. In practice it often turns out to be infinite, even for quite simple models such as the Poisson and Geometric fam…