Signal Recovery by Stochastic Optimization


Citar

Texto integral

Acesso aberto Acesso aberto
Acesso é fechado Acesso está concedido
Acesso é fechado Somente assinantes

Resumo

We discuss an approach to signal recovery in Generalized Linear Models (GLM) in which the signal estimation problem is reduced to the problem of solving a stochastic monotone Variational Inequality (VI). The solution to the stochastic VI can be found in a computationally efficient way, and in the case when the VI is strongly monotone we derive finite-time upper bounds on the expected ‖ · ‖22 error converging to 0 at the rate O(1/K) as the number K of observation grows. Our structural assumptions are essentially weaker than those necessary to ensure convexity of the optimization problem resulting from Maximum Likelihood estimation. In hindsight, the approach we promote can be traced back directly to the ideas behind the Rosenblatt’s perceptron algorithm.

Sobre autores

A. Juditsky

LJK, Université Grenoble Alpes

Autor responsável pela correspondência
Email: aanatoli.juditsky@univ-grenoble-alpes.fr
França, Saint-Martin-d’Hères

A. Nemirovski

ISyE, Georgia Institute of Technology

Email: aanatoli.juditsky@univ-grenoble-alpes.fr
Estados Unidos da América, Atlanta, Georgia

Arquivos suplementares

Arquivos suplementares
Ação
1. JATS XML

Declaração de direitos autorais © Pleiades Publishing, Inc., 2019