James C. Spall

Efficient Implementation of Second-Order Stochastic Approximation Algorithms in High-Dimensional Problems

View CodeNotebook

Stochastic approximation (SA) algorithms have been widely applied in minimization problems where the loss functions and/or the gradient are only accessible through noisy evaluations. Among all the SA algorithms, the second-order simultaneous perturbation stochastic approximation (2SPSA) and the second-order stochastic gradient (2SG) are particularly efficient in high-dimensional problems covering both gradient-free and gradient-based scenarios. However, due to the necessary matrix operations, the per-iteration floating-point-operation cost of the original 2SPSA/2SG is $ O(p^3) $ with $ p $ being the dimension of the underlying parameter. Note that the $O(p^3)$ floating-point-operation cost is distinct from the classical SPSA-based per-iteration $O(1)$ cost in terms of the number of noisy function evaluations. In this work, we propose a technique to efficiently implement the 2SPSA/2SG algorithms via the symmetric indefinite matrix factorization and show that the per-iteration floating-point-operation cost is reduced from $ O(p^3) $ to $ O(p^2) $. The almost sure convergence and rate of convergence for the newly-proposed scheme are inherited from the original 2SPSA/2SG naturally. The numerical improvement manifests its superiority in numerical studies in terms of computational complexity and numerical stability.

Via