We consider the problem of finding second-order stationary points in the optimization of
heterogeneous federated learning (FL). Previous works in FL mostly focus on first-order …

Federated Learning (FL) is an emerging paradigm that allows for decentralized machine
learning (ML), where multiple models are collaboratively trained in a privacy-preserving …

Motivated by understanding and analysis of large-scale machine learning under heavy-
tailed gradient noise, we study distributed optimization with smoothed gradient clipping, ie …

Decentralized learning is appealing as it enables the scalable usage of large amounts of
distributed data and resources (without resorting to any central entity), while promoting …

The increasing usage of streaming data has raised significant privacy concerns in
decentralized optimization and learning applications. To address this issue, differential …

Federated Learning (FL) is an emerging paradigm that allows for decentralized machine
learning (ML), where multiple models are collaboratively trained in a privacy-preserving …

Most existing decentralized learning methods with differential privacy (DP) employ fixed-
level Gaussian noise during training, regardless of gradient convergence, which …