9 papers
Decentralized SGD with Controlled Disagreement Finds Flatter Minima
Zesen Wang, Mikael Johansson
Decentralized training is often regarded as inferior to centralized training because the consensus errors between workers are thought to undermine convergence and generalization. T…
Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers
Samuel Erickson, Mikael Johansson
In modern machine learning, parallelization of training is an important strategy for increasing scale. Asynchronous stochastic gradient descent (ASGD), which maximizes the utilizat…
Byzantine-Robust Federated Learning with Learnable Aggregation Weights
Javad Parsa, Amir Hossein Daghestani, André M. H. Teixeira +1
Federated Learning (FL) enables clients to collaboratively train a global model without sharing their private data. However, the presence of malicious (Byzantine) clients poses sig…
Personalized Federated Learning under Model Dissimilarity Constraints
Samuel Erickson, Mikael Johansson
One of the defining challenges in federated learning is that of statistical heterogeneity among clients. We address this problem with KARULA, a regularized strategy for personalize…
Locally Differentially Private Online Federated Learning With Correlated Noise
Jiaojiao Zhang, Linglingzhi Zhu, Dominik Fay +1
We introduce a locally differentially private (LDP) algorithm for online federated learning that employs temporally correlated noise to improve utility while preserving privacy. To…
Non-convex composite federated learning with heterogeneous data
Jiaojiao Zhang, Jiang Hu, Mikael Johansson
We propose an innovative algorithm for non-convex composite federated learning that decouples the proximal operator evaluation and the communication between server and clients. Mor…