activity
20182021
most citedEscaping Saddle Points Faster with Stochastic Momentum

7 citations · 7 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG20217 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…

cs.LG2020

Understanding How Over-Parametrization Leads to Acceleration: A case of learning a single teacher neuron

Jun-Kun Wang, Jacob Abernethy

Over-parametrization has become a popular technique in deep learning. It is observed that by over-parametrization, a larger neural network needs a fewer training iterations than a…

cs.LG2018

Revisiting Projection-Free Optimization for Strongly Convex Constraint Sets

Jarrid Rector-Brooks, Jun-Kun Wang, Barzan Mozafari

We revisit the Frank-Wolfe (FW) optimization under strongly convex constraint sets. We provide a faster convergence rate for FW without line search, showing that a previously overl…

cs.LG2018

Acceleration through Optimistic No-Regret Dynamics

Jun-Kun Wang, Jacob Abernethy

We consider the problem of minimizing a smooth convex function by reducing the optimization to computing the Nash equilibrium of a particular zero-sum convex-concave game. Zero-sum…

cs.LG2018

Faster Rates for Convex-Concave Games

Jacob Abernethy, Kevin A. Lai, Kfir Y. Levy +1

We consider the use of no-regret algorithms to compute equilibria for particular classes of convex-concave games. While standard regret bounds would lead to convergence rates on th…