Descent Direction Stochastic Approximation Algorithm with Adaptive Step Sizes

Lužanin, Zorana and Stojkovska, Irena and Kresoja, Milena (2019) Descent Direction Stochastic Approximation Algorithm with Adaptive Step Sizes. Journal of Computational Mathematics, 37 (1). pp. 76-94. ISSN 0254-9409

Text luzanin. et al.pdf - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (246kB)

Abstract

A stochastic approximation (SA) algorithm with new adaptive step sizes for solving unconstrained minimization problems in noisy environment is proposed. New adaptive step size scheme uses ordered statistics of fixed number of previous noisy function values as a criterion for accepting good and rejecting bad steps. The scheme allows the algorithm to move in bigger steps and avoid steps proportional to 1/k when it is expected that larger steps will improve the performance. An algorithm with the new adaptive scheme is defined for a general descent direction. The almost sure convergence is established. The performance of new algorithm is tested on a set of standard test problems and compared with relevant algorithms. Numerical results support theoretical expectations and verify efficiency of the algorithm regardless of chosen search direction and noise level. Numerical results on problems arising in machine learning are also presented. Linear regression problem is considered using real data set. The results suggest that the proposed algorithm shows promise.

Actions (login required)

View Item