Frontiers to the learning of nonparametric hidden Markov models
From MaRDI portal
Publication:6441850
arXiv2306.16293MaRDI QIDQ6441850FDOQ6441850
Authors: Kweku Abraham, Elisabeth Gassiat, Zacharie Naulet 
Publication date: 28 June 2023
Abstract: Hidden Markov models (HMMs) are flexible tools for clustering dependent data coming from unknown populations, allowing nonparametric modelling of the population densities. Identifiability fails when the data is in fact independent, and we study the frontier between learnable and unlearnable two-state nonparametric HMMs. Interesting new phenomena emerge when the cluster distributions are modelled via density functions (the 'emission' densities) belonging to standard smoothness classes compared to the multinomial setting. Notably, in contrast to the multinomial setting previously considered, the identification of a direction separating the two emission densities becomes a critical, and challenging, issue. Surprisingly, it is possible to "borrow strength" from estimators of the smoother density to improve estimation of the other. We conduct precise analysis of minimax rates, showing a transition depending on the relative smoothnesses of the emission densities.
Nonparametric estimation (62G05) Density estimation (62G07) Markov processes: estimation; hidden Markov models (62M05)
This page was built for publication: Frontiers to the learning of nonparametric hidden Markov models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6441850)
