SPSA
SPSA stands for Stochastic Parallel Search Algorithm. It is an optimization algorithm used to find the minimum or maximum of a function. SPSA is particularly well-suited for optimizing functions that are noisy or where the gradient is difficult to compute directly. It belongs to the class of simultaneous perturbation stochastic approximation algorithms.
The core idea behind SPSA is to estimate the gradient of the function using randomly perturbed function
SPSA is often used in control systems, machine learning, and other fields where optimizing performance metrics