Distributed random reshuffling over networks
In this paper, we consider distributed optimization problems where agents, each possessing
a local cost function, collaboratively minimize the average of the local cost functions over a …
a local cost function, collaboratively minimize the average of the local cost functions over a …
Variance-reduced reshuffling gradient descent for nonconvex optimization: Centralized and distributed algorithms
Nonconvex finite-sum optimization plays a crucial role in signal processing and machine
learning, fueling the development of numerous centralized and distributed stochastic …
learning, fueling the development of numerous centralized and distributed stochastic …
Distributed Online Convex Optimization With Statistical Privacy
M Dai, DWC Ho, B Zhang, D Yuan… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
We focus on the problem of distributed online constrained convex optimization with
statistical privacy in multiagent systems. The participating agents aim to collaboratively …
statistical privacy in multiagent systems. The participating agents aim to collaboratively …
Stagewise Training With Exponentially Growing Training Sets
In the world of big data, training large-scale machine learning problems has gained
considerable attention. Numerous innovative optimization strategies have been presented in …
considerable attention. Numerous innovative optimization strategies have been presented in …
On the Convergence of Decentralized Stochastic Gradient Descent with Biased Gradients
Y Jiang, H Kang, J Liu, D Xu - IEEE Transactions on Signal …, 2025 - ieeexplore.ieee.org
Stochastic optimization algorithms are widely used to solve large-scale machine learning
problems. However, their theoretical analysis necessitates access to unbiased estimates of …
problems. However, their theoretical analysis necessitates access to unbiased estimates of …
Distributed random reshuffling methods with improved convergence
This paper proposes two distributed random reshuffling methods, namely Gradient Tracking
with Random Reshuffling (GT-RR) and Exact Diffusion with Random Reshuffling (ED-RR), to …
with Random Reshuffling (GT-RR) and Exact Diffusion with Random Reshuffling (ED-RR), to …
On Improved Distributed Random Reshuffling over Networks
In this paper, we consider a distributed optimization problem. A network of n agents, each
with its own local loss function, aims to collaboratively minimize the global average loss. We …
with its own local loss function, aims to collaboratively minimize the global average loss. We …