activity
20082022
most citedGeneralized power method for sparse principal component analysis

500 citations · 1.3k across the 50 of their papers we have counts for

collaborators
Showing cs.LGShow all

35 papers · 1 filter

cs.LG2022

Improved Stein Variational Gradient Descent with Importance Weights

Lukang Sun, Peter Richtárik

Stein Variational Gradient Descent (SVGD) is a popular sampling algorithm used in various machine learning tasks. It is well known that SVGD arises from a discretization of the ker…

cs.LG20221 cited

Adaptive Compression for Communication-Efficient Distributed Training

Maksim Makarenko, Elnur Gasanov, Rustem Islamov +2

We propose Adaptive Compressed Gradient Descent (AdaCGD) - a novel optimization algorithm for communication-efficient training of supervised machine learning models with adaptive c…

cs.LG2022

Federated Random Reshuffling with Compression and Variance Reduction

Grigory Malinovsky, Peter Richtárik

Random Reshuffling (RR), which is a variant of Stochastic Gradient Descent (SGD) employing sampling without replacement, is an immensely popular method for training supervised mach…

cs.LG20212 cited

Permutation Compressors for Provably Faster Distributed Nonconvex Optimization

Rafał Szlendak, Alexander Tyurin, Peter Richtárik

We study the MARINA method of Gorbunov et al (2021) -- the current state-of-the-art distributed non-convex optimization method in terms of theoretical communication complexity. The…

cs.LG20213 cited

Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information

Majid Jahani, Sergey Rusakov, Zheng Shi +3

We present a novel adaptive optimization algorithm for large-scale machine learning problems. Equipped with a low-cost estimate of local curvature and Lipschitz smoothness, our met…

cs.LG20218 cited

FedPAGE: A Fast Local Stochastic Gradient Method for Communication-Efficient Federated Learning

Haoyu Zhao, Zhize Li, Peter Richtárik

Federated Averaging (FedAvg, also known as Local-SGD) (McMahan et al., 2017) is a classical federated learning algorithm in which clients run multiple local SGD steps before commun…