Linearly Converging Error Compensated SGD

1 code implementation • NeurIPS 2020 • Eduard Gorbunov, Dmitry Kovalev, Dmitry Makarenko, Peter Richtárik

Moreover, using our general scheme, we develop new variants of SGD that combine variance reduction or arbitrary sampling with error feedback and quantization and derive the convergence rates for these methods beating the state-of-the-art results.

Quantization