7 citations · 8 across the 5 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
math.OC2021
Understanding Modern Techniques in Optimization: Frank-Wolfe, Nesterov's Momentum, and Polyak's Momentum
Jun-Kun Wang
In the first part of this dissertation research, we develop a modular framework that can serve as a recipe for constructing and analyzing iterative algorithms for convex optimizati…
cs.LG2021★ 7 cited
Escaping Saddle Points Faster with Stochastic Momentum
Jun-Kun Wang, Chi-Heng Lin, Jacob Abernethy
Stochastic gradient descent (SGD) with stochastic momentum is popular in nonconvex stochastic optimization and particularly for the training of deep neural networks. In standard SG…