activity
20192024
most citedL-SVRG and L-Katyusha with Arbitrary Sampling

11 citations · 42 across the 8 of their papers we have counts for

collaborators

9 papers

cs.LG20212 cited

Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning

Xun Qian, Rustem Islamov, Mher Safaryan +1

Recent advances in distributed optimization have shown that Newton-type methods with proper communication compression mechanisms can guarantee fast local rates and low communicatio…

math.OC20211 cited

Error Compensated Loopless SVRG, Quartz, and SDCA for Distributed Optimization

Xun Qian, Hanze Dong, Peter Richtárik +1

The communication of gradients is a key bottleneck in distributed training of large scale machine learning models. In order to reduce the communication cost, gradient compression (…

cs.LG202111 cited

Distributed Second Order Methods with Fast Rates and Compressed Communication

Rustem Islamov, Xun Qian, Peter Richtárik

We develop several new communication-efficient second-order methods for distributed optimization. Our first method, NEWTON-STAR, is a variant of Newton's method from which it inher…

math.OC20208 cited

Error Compensated Distributed SGD Can Be Accelerated

Xun Qian, Peter Richtárik, Tong Zhang

Gradient compression is a recent and increasingly popular technique for reducing the communication cost in distributed training of large-scale machine learning models. In this work…

math.OC2020

Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization

Zhize Li, Dmitry Kovalev, Xun Qian +1

Due to the high communication cost in distributed and federated learning problems, methods relying on compression of communicated messages are becoming increasingly popular. While…

math.OC201911 cited

L-SVRG and L-Katyusha with Arbitrary Sampling

Xun Qian, Zheng Qu, Peter Richtárik

We develop and analyze a new family of {\em nonaccelerated and accelerated loopless variance-reduced methods} for finite sum optimization problems. Our convergence analysis relies…