Decentralized Accelerated Proximal Gradient Descent

Authors: Haishan Ye, Ziang Zhou, Luo Luo, Tong Zhang

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our empirical study shows that the proposed algorithm outperforms existing state-of-the-art algorithms.
Researcher Affiliation Academia 1Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen 2Department of Mathematics, The Hong Kong University of Science and Technology
Pseudocode Yes Algorithm 1 DPAG; Algorithm 2 Fast Mix
Open Source Code No The paper does not provide an explicit statement about releasing source code or a link to a code repository.
Open Datasets No The paper mentions using 'datasets w8a and w9a which can be downloaded in libsvm datasets.' but does not provide a specific link, DOI, or formal citation with authors/year for public access.
Dataset Splits No The paper does not provide specific dataset split information, only mentioning the total number of agents and data points.
Hardware Specification No The paper does not specify any hardware details like GPU/CPU models or types of machines used for experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup Yes Experiments Setting In our experiments, we consider random networks where each pair of agents have a connection with a probability of p = 0.1. We set W = I L λ1(L) where L is the Laplacian matrix associated with a weighted graph, and λ1(L) is the largest eigenvalue of L. We set m = 100, that is, there exists 100 agents in this network. In our experiments, the gossip matrix W satisfies 1 λ2(W) = 0.05. ... We set σ1 = 10 4 for all datasets and set σ2 as 10 3, 10 4 and 10 5 to control the condition number of the objective function. ... In the experiments, we set K = 1, 2, 3 respectively.