Mini-batch stochastic gradient descent with dynamic sample sizes
From MaRDI portal
Abstract: We focus on solving constrained convex optimization problems using mini-batch stochastic gradient descent. Dynamic sample size rules are presented which ensure a descent direction with high probability. Empirical results from two applications show superior convergence compared to fixed sample implementations.
This page was built for publication: Mini-batch stochastic gradient descent with dynamic sample sizes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6289671)
