To mitigate the privacy leakages and communication burdens of Federated Learning (FL), decentralized FL (DFL) discards the central server and each client only communicates with …
Decentralized optimization to minimize a finite sum of functions, distributed over a network of nodes, has been a significant area within control and signal-processing research due to its …
Z Li, H Zhao, B Li, Y Chi - Advances in Neural Information …, 2022 - proceedings.neurips.cc
To enable large-scale machine learning in bandwidth-hungry environments such as wireless networks, significant progress has been made recently in designing communication …
R Xin, UA Khan, S Kar - IEEE Transactions on Signal …, 2020 - ieeexplore.ieee.org
This paper describes a novel algorithmic framework to minimize a finite-sum of functions available over a network of nodes. The proposed framework, that we call GT-VR, is …
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 Beznosikov, G Scutari, A Rogozin… - Advances in Neural …, 2021 - proceedings.neurips.cc
We study solution methods for (strongly-) convex-(strongly)-concave Saddle-Point Problems (SPPs) over networks of two type--master/workers (thus centralized) architectures and mesh …
Communication efficiency has been widely recognized as the bottleneck for large-scale decentralized machine learning applications in multi-agent or federated environments. To …
This paper considers the decentralized convex optimization problem, which has a wide range of applications in large-scale machine learning, sensor networks, and control theory …
R Xin, UA Khan, S Kar - SIAM Journal on Optimization, 2022 - SIAM
This paper considers decentralized minimization of N:=nm smooth nonconvex cost functions equally divided over a directed network of n nodes. Specifically, we describe a stochastic …