Aryan Mokhtari

DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate

2020 · King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)

In this paper, we consider distributed algorithms for solving the empirical risk minimization problem under the master/worker
\ncommunication model. We develop a distributed asynchronous quasi-Newton algorithm that can achieve superlinear convergence. To our knowledge, this is …

Network Adaptive Federated Learning: Congestion and Lossy Compression

2023 · arXiv (Cornell University)

In order to achieve the dual goals of privacy and learning across distributed data, Federated Learning (FL) systems rely on frequent exchanges of large files (model updates) between a set of clients and the server. …