Goto

Collaborating Authors

 contraction compressor



Error Compensated Distributed SGD can be Accelerated

Neural Information Processing Systems

In this work, we show for the first time that error compensated gradient compression methods can be accelerated. In particular, we propose and study the error compensated loopless Katyusha method, and establish an accelerated linear convergence rate under standard assumptions.


Error Compensated Distributed SGD can be Accelerated

Neural Information Processing Systems

In this work, we show for the first time that error compensated gradient compression methods can be accelerated. In particular, we propose and study the error compensated loopless Katyusha method, and establish an accelerated linear convergence rate under standard assumptions.