Timezone: »

Decentralized Accelerated Proximal Gradient Descent
Haishan Ye · Ziang Zhou · Luo Luo · Tong Zhang

Tue Dec 08 09:00 PM -- 11:00 PM (PST) @ 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.

Author Information

Haishan Ye (The Chinese University of Hong Kong, Shenzen)
Ziang Zhou (The Hong Kong Polytechnic University)
Luo Luo (The Hong Kong University of Science and Technology)
Tong Zhang (The Hong Kong University of Science and Technology)

More from the Same Authors