2007/01/28 by Florencia Leonardi, Leonardi, Florencia
Computer Science · Mathematics · #60G10 (Secondary) #62M09 (Primary) 62F12 #Algorithms and Data Compression #Bayesian Methods and Mixture Models #Bayesian Modeling and Causal Inference #FOS: Mathematics #Machine Learning and Algorithms #Probability (math.PR) #Statistical Methods and Inference #Statistics Theory (math.ST) #math.PR #math.ST #msc:60G10 #msc:62F12 #msc:62M09 #stat.TH
paper · pdf · doi:10.48550/arxiv.math/0701810
13 pages, some changes in the organization of the paper from previous version
openalex publication_date 2007/01/28 · arxiv created 2009/03/11 · arxiv updated 2009/12/01 · openalex created_date 2022/10/02 · openalex updated_date 2026/07/28
We find upper bounds for the probability of underestimation and overestimation errors in penalized likelihood context tree estimation. The bounds are explicit and applies to processes of not necessarily finite memory. We allow for general penalizing terms and we give conditions over the maximal depth of the estimated trees in order to get strongly consistent estimates. This generalizes previous results obtained in the case of estimation of the order of a Markov chain.