activity
20142026
most citedSimple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization

8 citations · 17 across the 18 of their papers we have counts for

collaborators
Showing 2017Show all

2 papers · 1 filter

math.OC2017★ 5 cited

Mini-batch stochastic gradient descent with dynamic sample sizes

Michael R. Metel

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…

math.OC2017★ 1 cited

Kelly betting on horse races with uncertainty in probability estimates

Michael R. Metel

We investigate the problem of gambling with uncertainty in outcome probabilities. Stochastic optimization models are proposed for optimal investing on events with mutually exclusiv…