most citedStochastic Distributed Learning with Gradient Quantization and Variance Reduction

81 citations · 116 across the 5 of their papers we have counts for

collaborators

5 papers

math.OC20202 cited

Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems

Filip Hanzely, Dmitry Kovalev, Peter Richtarik

We propose an accelerated version of stochastic variance reduced coordinate descent -- ASVRCD. As other variance reduced coordinate descent methods such as SEGA or SVRCD, our metho…

cs.LG20196 cited

Distributed Fixed Point Methods with Compressed Iterates

Sélim Chraibi, Ahmed Khaled, Dmitry Kovalev +3

We propose basic and natural assumptions under which iterative optimization methods with compressed iterates can be analyzed. This problem is motivated by the practice of federated…

cs.LG201916 cited

Stochastic Newton and Cubic Newton Methods with Simple Local Linear-Quadratic Rates

Dmitry Kovalev, Konstantin Mishchenko, Peter Richtárik

We present two new remarkably simple stochastic second-order methods for minimizing the average of a very large number of sufficiently smooth and strongly convex functions. The fir…

math.OC201981 cited

Stochastic Distributed Learning with Gradient Quantization and Variance Reduction

Samuel Horváth, Dmitry Kovalev, Konstantin Mishchenko +2

We consider distributed optimization where the objective function is spread among different devices, each sending incremental model updates to a central server. To alleviate the co…

cs.LG201911 cited

Don't Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop

Dmitry Kovalev, Samuel Horvath, Peter Richtarik

The stochastic variance-reduced gradient method (SVRG) and its accelerated variant (Katyusha) have attracted enormous attention in the machine learning community in the last few ye…