activity
20182023
most citedDecentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication

185 citations · 227 across the 9 of their papers we have counts for

collaborators

15 papers

cs.LG2023

On Convergence of Incremental Gradient for Non-Convex Smooth Functions

Anastasia Koloskova, Nikita Doikov, Sebastian U. Stich +1

In machine learning and neural network optimization, algorithms like incremental gradient, and shuffle SGD are popular due to minimizing the number of cache misses and good practic…

cs.LG2023★ 4 cited

Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees

Anastasia Koloskova, Hadrien Hendrikx, Sebastian U. Stich

Gradient clipping is a popular modification to standard (stochastic) gradient descent, at every iteration limiting the gradient norm to a certain value . It is widely used fo…

cs.LG2023

Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy

Anastasia Koloskova, Ryan McKenna, Zachary Charles +2

We study gradient descent under linearly correlated noise. Our work is motivated by recent practical methods for optimization with differential privacy (DP), such as DP-FTRL, which…

math.OC2023★ 1 cited

Decentralized Gradient Tracking with Local Steps

Yue Liu, Tao Lin, Anastasia Koloskova +1

Gradient tracking (GT) is an algorithm designed for solving decentralized optimization problems over a network (such as training a machine learning model). A key feature of GT is a…

cs.LG2022★ 18 cited

Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning

Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi

We study the asynchronous stochastic gradient descent algorithm for distributed training over workers which have varying computation and communication frequency over time. In t…

cs.LG2022★ 8 cited

Data-heterogeneity-aware Mixing for Decentralized Learning

Yatin Dandi, Anastasia Koloskova, Martin Jaggi +1

Decentralized learning provides an effective framework to train machine learning models with data distributed over arbitrary communication graphs. However, most existing approaches…