RUS  ENG
Full version
JOURNALS // Zhurnal Vychislitel'noi Matematiki i Matematicheskoi Fiziki // Archive

Zh. Vychisl. Mat. Mat. Fiz., 2024 Volume 64, Number 4, Pages 627–636 (Mi zvmmf11730)

Optimal control

Polyak’s method based on the stochastic Lyapunov function for justifying the consistency of estimates produced by a stochastic approximation search algorithm under an unknown-but-bounded noise

O. N. Granichinab, Yu. V. Ivanskiia, K. D. Kopylovaa

a St. Petersburg State University, 199034, St. Petersburg, Russia
b Mechanical Engineering Research Institute of the Russian Academy of Sciences, St. Petersburg, Russia

Abstract: In 1976–1977, Polyak published in the journal Avtomatica i Telemekhanika (Automation and Remote Control) two remarkable papers on how to study the properties of estimates of iterative pseudogradient algorithms. The first paper published in 1976 considered the general case based on the stochastic Lyapunov function, and the second one considered the linear case. The assumptions formulated in these papers and the estimates obtained in them can still be considered the state-of-the art. In the current paper, Polyak’s approach is applied to the study of the properties of estimates of a (randomized) stochastic approximation search algorithm for the case of unknown-but-bounded noise in observations. The obtained asymptotic estimates were already known earlier, and exact estimates for a finite number of observations are published for the first time.

Key words: stochastic approximation search algorithm, unknown-but-bounded noise, approximation of gradient, smoothing kernels, gradient-free methods, methods with inexact oracle.

UDC: 519.85

Received: 15.09.2023
Revised: 06.11.2023
Accepted: 20.11.2023

DOI: 10.31857/S0044466924040034


 English version:
Computational Mathematics and Mathematical Physics, 2024, 64:4, 771–780

Bibliographic databases:


© Steklov Math. Inst. of RAS, 2024