| Full text | |
| Author(s): |
Ost, G.
;
Reynaud-Bouret, P.
Total Authors: 2
|
| Document type: | Journal article |
| Source: | ANNALES DE L INSTITUT HENRI POINCARE-PROBABILITES ET STATISTIQUES; v. 56, n. 4, p. 29-pg., 2020-11-01. |
| Abstract | |
Inspired by Kalikow-type decompositions, we introduce a new stochastic model of infinite neuronal networks, for which we establish sharp oracle inequalities for Lasso methods and restricted eigenvalue properties for the associated Gram matrix with high probability. These results hold even if the network is only partially observed. The main argument rely on the fact that concentration inequalities can easily be derived whenever the transition probabilities of the underlying process admit a sparse space-time representation. (AU) | |
| FAPESP's process: | 13/07699-0 - Research, Innovation and Dissemination Center for Neuromathematics - NeuroMat |
| Grantee: | Oswaldo Baffa Filho |
| Support Opportunities: | Research Grants - Research, Innovation and Dissemination Centers - RIDC |