On universal algorithms for classifying and predicting stationary processes
Authors:
Open Access
- 1 January 2021
- journal article
- research article
- Published by Institute of Mathematical Statistics in Probability Surveys
- Vol. 18 (none) , 77-131
Abstract
This is a survey of results on universal algorithms for classification and prediction of stationary processes. The classification problems include discovering the order of a k-step Markov chain, determining memory words in finitarily Markovian processes and estimating the entropy of an unknown process. The prediction problems cover both discrete and real valued processes in a variety of situations. Both the forward and the backward prediction problems are discussed with the emphasis being on pointwise results. This survey is just a teaser. The purpose is merely to call attention to results on classification and prediction. We will refer the interested reader to the sources. Throughout the paper we will give illuminating examples.Keywords
This publication has 88 references indexed in Scilit:
- On the minimal penalty for Markov order estimationProbability Theory and Related Fields, 2010
- Rate of convergence of predictive distributions for dependent dataBernoulli, 2009
- Prediction for discrete time seriesProbability Theory and Related Fields, 2004
- Universal schemes for learning the best nonlinear predictor given the infinite past and side informationIEEE Transactions on Information Theory, 1999
- Limits to consistent on-line forecasting for ergodic time seriesIEEE Transactions on Information Theory, 1998
- A Topological Criterion for Hypothesis TestingThe Annals of Statistics, 1994
- Entropy and data compression schemesIEEE Transactions on Information Theory, 1993
- Predicting the future of functions on flowsTheory of Computing Systems, 1978
- A universal algorithm for sequential data compressionIEEE Transactions on Information Theory, 1977
- On Uniformly Consistent TestsThe Annals of Mathematical Statistics, 1951