198 citations · 379 across the 15 of their papers we have counts for
3 papers · 1 filter
Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs
Bin Hu, Stephen Wright, Laurent Lessard
Techniques for reducing the variance of gradient estimates used in stochastic programming algorithms for convex finite-sum problems have received a great deal of attention in recen…
ATOMO: Communication-efficient Learning via Atomic Sparsification
Hongyi Wang, Scott Sievert, Zachary Charles +3
Distributed model training suffers from communication overheads due to frequent gradient updates transmitted between compute nodes. To mitigate these overheads, several studies pro…
Blended Conditional Gradients: the unconditioning of conditional gradients
Gábor Braun, Sebastian Pokutta, Dan Tu +1
We present a blended conditional gradient approach for minimizing a smooth convex function over a polytope P, combining the Frank--Wolfe algorithm (also called conditional gradient…