27 citations · 65 across the 11 of their papers we have counts for
Showing 2021Show all
3 papers · 1 filter
math.OC2021★ 3 cited
Improving Dynamic Regret in Distributed Online Mirror Descent Using Primal and Dual Information
Nima Eshraghi, Ben Liang
We consider the problem of distributed online optimization, with a group of learners connected via a dynamic communication graph. The goal of the learners is to track the global mi…
cs.IT2021★ 2 cited
Gradient and Projection Free Distributed Online Min-Max Resource Optimization
Jingrong Wang, Ben Liang
We consider distributed online min-max resource allocation with a set of parallel agents and a parameter server. Our goal is to minimize the pointwise maximum over a set of time-va…
cs.LG2021★ 9 cited
On the Generalization of Stochastic Gradient Descent with Momentum
Ali Ramezani-Kebrya, Ashish Khisti, Ben Liang
While momentum-based methods, in conjunction with stochastic gradient descent (SGD), are widely used when training machine learning models, there is little theoretical understandin…