Constrained and Preconditioned Stochastic Gradient Method

DOI10.1109/TSP.2015.2412919zbMATH Open1394.94259DBLPjournals/tsp/JiangHWY15arXiv1508.07649WikidataQ56919771 ScholiaQ56919771MaRDI QIDQ4580583FDOQ4580583

Gang Huang, Liangkai Yu, Hong Jiang, Paul Wilford

Publication date: 22 August 2018

Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)

Abstract: We consider stochastic approximations which arise from such applications as data communications and image processing. We demonstrate why constraints are needed in a stochastic approximation and how a constrained approximation can be incorporated into a preconditioning technique to derive the pre-conditioned stochastic gradient method (PSGM). We perform convergence analysis to show that the PSGM converges to the theoretical best approximation under some simple assumptions on the preconditioner and on the independence of samples drawn from a stochastic process. Simulation results are presented to demonstrate the effectiveness of the constrained and precondi-tioned stochastic gradient method.

Full work available at URL: https://arxiv.org/abs/1508.07649

Mathematics Subject Classification ID

Markov processes: estimation; hidden Markov models (62M05) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Cited In (1)

• Predict-and-Recompute Conjugate Gradient Variants

This page was built for publication: Constrained and Preconditioned Stochastic Gradient Method

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4580583)