Stochastic analysis of Hyperslab-based adaptive projected subgradient method under bounded noise

Symeon Chouvardas, Konstantinos Slavakis, Sergios Theodoridis, Isao Yamada

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

This letter establishes a novel analysis of the Adaptive Projected Subgradient Method (APSM) in the intersection of the stochastic and robust estimation paradigms. Utilizing classical worst-case bounds on the noise process, drawn from the robust estimation methodology, the present study demonstrates that the hyperslab-inspired version of the APSM generates a sequence of estimates which converges to a point located, with probability one, arbitrarily close to the estimand. Numerical tests and comparisons with classical time-adaptive algorithms corroborate the theoretical findings of the study.

Original languageEnglish (US)
Article number6494588
Pages (from-to)729-732
Number of pages4
JournalIEEE Signal Processing Letters
Volume20
Issue number7
DOIs
StatePublished - 2013

Keywords

  • APSM
  • bounded noise
  • convergence
  • hyperslab

Fingerprint

Dive into the research topics of 'Stochastic analysis of Hyperslab-based adaptive projected subgradient method under bounded noise'. Together they form a unique fingerprint.

Cite this