A Damped Newton Method Achieves Global O(1/K²) and Local Quadratic Convergence Rate, Slavomír Hanzely, Dmitry Kamzolov, Dmitry Pasechnyuk, Alexander Gasnikov, Peter Richtárik, Martin Takáč
Martin Takac

Stochastic distributed learning with gradient quantization and double-variance reduction, Samuel Horváth, Dmitry Kovalev, Konstantin Mishchenko, Peter Richtárik, Sebastian Stich
Samuel Horváth

A Damped Newton Method Achieves Global O(1/K²) and Local Quadratic Convergence Rate, Slavomír Hanzely, Dmitry Kamzolov, Dmitry Pasechnyuk, Alexander Gasnikov, Peter Richtárik, Martin Takáč
Machine Learning Faculty Publications

Stochastic distributed learning with gradient quantization and double-variance reduction, Samuel Horváth, Dmitry Kovalev, Konstantin Mishchenko, Peter Richtárik, Sebastian Stich
Machine Learning Faculty Publications

Natural Compression for Distributed Deep Learning, Samuel Horváth, Chen Yu Ho, Horváth L'udovít, Atal Narayan Sahu, Marco Canini, Peter Richtárik
Machine Learning Faculty Publications

Adaptive Learning Rates for Faster Stochastic Gradient Methods, Samuel Horvath, Konstantin Mishchenko, Peter Richtárik
Machine Learning Faculty Publications

AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods, Zheng Shi, Abdurakhmon Sadiev, Nicolas Loizou, Peter Richtárik, Martin Takac
Martin Takac

FedShuffle: Recipes for Better Use of Local Work in Federated Learning, Samuel Horváth, Maziar Sanjabi, Lin Xiao, Peter Richtárik, Michael Rabbat
Machine Learning Faculty Publications

AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods, Zheng Shi, Abdurakhmon Sadiev, Nicolas Loizou, Peter Richtárik, Martin Takac
Machine Learning Faculty Publications