Name
Abstract | ||
|---|---|---|
Stochastic optimization plays an important role in solving many problems encountered in machine learning or adaptive processing. In this context, the second-order statistics of the data are often unknown a priori or their direct computation is too intensive, and they have to be estimated on-line from the related signals. In the context of batch optimization of an objective function being the sum of a data fidelity term and a penalization (e.g. a sparsity promoting function), Majorize-Minimize (MM) subspace methods have recently attracted much interest since they are fast, highly flexible and effective in ensuring convergence. The goal of this paper is to show how these methods can be successfully extended to the case when the cost function is replaced by a sequence of stochastic approximations of it. Simulation results illustrate the good practical performance of the proposed MM Memory Gradient (3MG) algorithm when applied to 2D filter identification. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.5281/zenodo.44156 | Signal Processing Conference |
Keywords | Field | DocType |
approximation theory,filtering theory,higher order statistics,optimisation,2D filter identification,MM memory gradient algorithm,adaptive processing,batch optimization,data fidelity term,machine learning,majorize-minimize subspace methods,second-order statistics,stochastic 3MG algorithm,stochastic approximations,Newton method,adaptive filtering,descent methods,filter identification,machine learning,majorization-minimization,memory gradient methods,optimization,recursive algorithms,sparsity,stochastic approximation,subspace algorithms | Convergence (routing),Stochastic optimization,Mathematical optimization,Subspace topology,Computer science,A priori and a posteriori,Algorithm,Adaptive filter,Stochastic approximation,Computation,Newton's method | Conference |
ISSN | Citations | PageRank |
2076-1465 | 3 | 0.36 |
References | Authors | |
9 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Emilie Chouzenoux | 1 | 202 | 26.37 |
| Jean-Christophe Pesquet | 2 | 206 | 22.24 |
| Anisia Florescu | 3 | 3 | 0.36 |