TY - JOUR
T1 - Stochastic analysis of Hyperslab-based adaptive projected subgradient method under bounded noise
AU - Chouvardas, Symeon
AU - Slavakis, Konstantinos
AU - Theodoridis, Sergios
AU - Yamada, Isao
PY - 2013
Y1 - 2013
N2 - 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.
AB - 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.
KW - APSM
KW - bounded noise
KW - convergence
KW - hyperslab
UR - http://www.scopus.com/inward/record.url?scp=84879049087&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84879049087&partnerID=8YFLogxK
U2 - 10.1109/LSP.2013.2257169
DO - 10.1109/LSP.2013.2257169
M3 - Article
AN - SCOPUS:84879049087
SN - 1070-9908
VL - 20
SP - 729
EP - 732
JO - IEEE Signal Processing Letters
JF - IEEE Signal Processing Letters
IS - 7
M1 - 6494588
ER -