Gradient Descent for Convex and Smooth Noisy Optimization

Feifei Hu, Mathieu Gerber

We study the use of gradient descent with backtracking line search (GD-BLS) to solve the noisy optimization problem ${\theta }_{\star }:={\mathrm{argmin}}_{\theta \in {\mathbb{R}}^d}\mathbb{E}[f(\theta ,Z)]$…