activity
20172022
most citedDecentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication

185 citations · 707 across the 16 of their papers we have counts for

collaborators

33 papers

cs.LG20228 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…

cs.LG20221 cited

Tackling benign nonconvexity with smoothing and stochastic gradients

Harsh Vardhan, Sebastian U. Stich

Non-convex optimization problems are ubiquitous in machine learning, especially in Deep Learning. While such complex problems can often be successfully optimized in practice by usi…

cs.DC20227 cited

An Improved Analysis of Gradient Tracking for Decentralized Machine Learning

Anastasia Koloskova, Tao Lin, Sebastian U. Stich

We consider decentralized machine learning over a network where the training data is distributed across agents, each of which can compute stochastic model updates on their loca…

cs.LG2022

Characterizing & Finding Good Data Orderings for Fast Convergence of Sequential Gradient Methods

Amirkeivan Mohtashami, Sebastian Stich, Martin Jaggi

While SGD, which samples from the data with replacement is widely studied in theory, a variant called Random Reshuffling (RR) is more common in practice. RR iterates through random…

cs.LG2021

On Second-order Optimization Methods for Federated Learning

Sebastian Bischoff, Stephan Günnemann, Martin Jaggi +1

We consider federated learning (FL), where the training data is distributed across a large number of clients. The standard optimization method in this setting is Federated Averagin…

stat.ML2021

Semantic Perturbations with Normalizing Flows for Improved Generalization

Oguz Kaan Yuksel, Sebastian U. Stich, Martin Jaggi +1

Data augmentation is a widely adopted technique for avoiding overfitting when training deep neural networks. However, this approach requires domain-specific knowledge and is often…