Consistency of Feature Markov Processes
From MaRDI portal
Prediction theory (aspects of stochastic processes) (60G25) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Computational learning theory (68Q32) Probability in computer science (algorithm analysis, random structures, phase transitions, etc.) (68Q87) Learning and adaptive systems in artificial intelligence (68T05)
Abstract: We are studying long term sequence prediction (forecasting). We approach this by investigating criteria for choosing a compact useful state representation. The state is supposed to summarize useful information from the history. We want a method that is asymptotically consistent in the sense it will provably eventually only choose between alternatives that satisfy an optimality property related to the used criterion. We extend our work to the case where there is side information that one can take advantage of and, furthermore, we briefly discuss the active setting where an agent takes actions to achieve desirable outcomes.
Recommendations
- scientific article; zbMATH DE number 5770656
- Consistency for parametric interval Markov chains
- Fitting feature-dependent Markov chains
- Consistency and refinement for interval Markov chains
- Bayesian consistency for Markov models
- scientific article; zbMATH DE number 1045396
- scientific article; zbMATH DE number 3951715
- Consistency of Maximum Likelihood Estimators for Multiparameter Markov Chains
- Strong Markov properties for Markov random fields
This page was built for publication: Consistency of Feature Markov Processes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4930710)
