5 papers
Achieving Linear Speedup for Composite Federated Learning
Kun Huang, Shi Pu, Karl Henrik Johansson
This paper proposes FedNMap, a normal map-based method for composite federated learning, where the objective consists of a smooth loss and a possibly nonsmooth regularizer. FedNMap…
Distributed Normal Map-based Stochastic Proximal Gradient Methods over Networks
Kun Huang, Shi Pu, Angelia NediÄ
Consider agents connected over a network collaborating to minimize the average of their local cost functions combined with a common nonsmooth function. This paper introduces a…
Distributed Stochastic Momentum Tracking with Local Updates: Achieving Optimal Communication and Iteration Complexities
Kun Huang, Shi Pu
We propose Local Momentum Tracking (LMT), a novel distributed stochastic gradient method for solving distributed optimization problems over networks. To reduce communication overhe…
Decentralized Min-Max Optimization with Gradient Tracking
Runze You, Kun Huang, Shi Pu
This paper presents a novel distributed formulation of the min-max optimization problem. Such a formulation enables enhanced flexibility among agents when optimizing their maximiza…
An Accelerated Distributed Stochastic Gradient Method with Momentum
Kun Huang, Shi Pu, Angelia NediÄ
In this paper, we introduce an accelerated distributed stochastic gradient method with momentum for solving the distributed optimization problem, where a group of agents collab…