4 papers
Reduction and classification of higher-order Markov chains
Christophe Gallesco, Caio Teodore Genovese Huss Oliveira, Daniel Yasumasa Takahashi
We study the class structure of finite-alphabet Markov chains with arbitrary memory length. To capture the structural constraints induced by prohibited transitions, we introduce th…
Uniqueness of stationary compatible probability measures for chains of infinite order with forbidden transitions
Christophe Gallesco, Sandro Gallo, Daniel Yasumasa Takahashi
In this paper, we consider chains of infinite order on countable state spaces with prohibited transitions. We give a set of sufficient conditions on the structure of the probabilit…
Pathwise guessing in categorical time series with unbounded alphabets
J. -R. Chazottes, S. Gallo, D. Takahashi
The following learning problem arises naturally in various applications: Given a finite sample from a categorical or count time series, can we learn a function of the sample that (…
Optimal Gaussian concentration bounds for stochastic chains of unbounded memory
J. -R. Chazottes, S. Gallo, D. Takahashi
We obtain optimal Gaussian concentration bounds (GCBs) for stochastic chains of unbounded memory (SCUMs) on countable alphabets. These stochastic processes are also known as "chain…