| Texto completo | |
| Autor(es): |
Chazottes, Jean-Rene
;
Gallo, Sandro
;
Takahashi, Daniel Y.
Número total de Autores: 3
|
| Tipo de documento: | Artigo Científico |
| Fonte: | ANNALS OF APPLIED PROBABILITY; v. 33, n. 5, p. 30-pg., 2023-10-01. |
| Resumo | |
Stochastic chains of unbounded memory (SCUMs) are generalization of Markov chains, also known in the literature as "chains with complete con-nections" or "g-measures". We obtain Gaussian concentration bounds (GCB) in this large class of models, for general alphabets, under two different con-ditions on the kernel: (1) when the sum of its oscillations is less than one, or (2) when the sum of its variations is finite, that is, belongs to l(1)(N). We also obtain explicit constants as functions of the parameters of the model. Our conditions are sharp in the sense that we exhibit examples of SCUMs that do not have GCB and for which the sum of oscillations is 1 + is an element of, or the variation belongs to l(1+is an element of)(N) for any e > 0. These examples are based on the existence of phase transitions.We illustrate our results with four applications. First, we derive a Dvoretzky-Kiefer-Wolfowitz-type inequality which gives a uniform control on the fluctuations of the empirical measure. Second, in the finite-alphabet case, we obtain an upper bound on the d -distance between two stationary SCUMs and, as a by-product, we obtain new explicit bounds on the speed of Markovian approximation in d . Third, we derive new bounds on the fluctu-ations of the "plug-in" estimator for entropy. Fourth, we obtain new rate of convergence for the maximum likelihood estimator of conditional probability. (AU) | |
| Processo FAPESP: | 17/07084-6 - Propriedades estatísticas da recorrência de Poincaré e teoria dos valores extremos |
| Beneficiário: | Alexsandro Giacomo Grimbert Gallo |
| Modalidade de apoio: | Bolsas no Exterior - Pesquisa |
| Processo FAPESP: | 19/23439-4 - Cadeias de longo alcance e passeios aleatórios em grafos |
| Beneficiário: | Alexsandro Giacomo Grimbert Gallo |
| Modalidade de apoio: | Auxílio à Pesquisa - Regular |