Skip to yearly menu bar Skip to main content


Decentralized Accelerated Proximal Gradient Descent

Haishan Ye · Ziang Zhou · Luo Luo · Tong Zhang

Poster Session 2 #657


Decentralized optimization has wide applications in machine learning, signal processing, and control. In this paper, we study the decentralized composite optimization problem with a non-smooth regularization term. Many proximal gradient based decentralized algorithms have been proposed in the past. However, these algorithms do not achieve near optimal computational complexity and communication complexity. In this paper, we propose a new method which establishes the optimal computational complexity and a near optimal communication complexity. Our empirical study shows that the proposed algorithm outperforms existing state-of-the-art algorithms.

Chat is not available.