Paper accepted to ICML 2021

Our paper “ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networks” was accepted to The Thirty-eighth International Conference on Machine Learning ( ICML 2021), which will be run virtually during July 18-24. This is a joint work with Dmitry Kovalev, Peter Richtárik, Alexander Rogozin and Alexander Gasnikov. We were informed that the acceptance rate this year is around 21%.

Here you can find a YouTube recording of my short 5-minute talk about it.