Stochastic Analysis of Hyperslab-Based Adaptive Projected Subgradient Method Under Bounded Noise

Symeon Chouvardas, Konstantinos Slavakis, Sergios Theodoridis, Isao Yamada

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.