A Linearly Convergent Proximal Gradient Algorithm for Decentralized Optimization

Authors: Sulaiman Alghunaim, Kun Yuan, Ali H. Sayed

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We remark that simulations of the proposed algorithm are provided in Section B in the supplementary material.
Researcher Affiliation Academia Sulaiman A. Alghunaim, Kun Yuan Electrical and Computer Engineering Department University of California Los Angeles Los Angeles, CA, 90095 {salghunaim,kunyuan}@ucla.edu Ali H. Sayed Ecole Polytechnique Fédérale de Lausanne CH-1015 Lausanne, Switzerland ali.sayed@epfl.ch
Pseudocode Yes Algorithm (Proximal Primal-Dual Diffusion P2D2) Setting: Let B = 0.5(I A) = [bsk] and choose step-sizes µ and α. Set all initial variables to zero and repeat for i = 1, 2,...
Open Source Code No The paper does not provide any concrete access (link or explicit statement) to the source code for the methodology described.
Open Datasets No The paper mentions simulations but does not provide any information about specific datasets used or their public availability.
Dataset Splits No The paper does not provide information on dataset splits (train, validation, test).
Hardware Specification No The paper does not specify any hardware details (GPU/CPU models, memory, etc.) used for running experiments.
Software Dependencies No The paper does not list any specific software dependencies with version numbers.
Experiment Setup No The paper defines tunable step-sizes µ and α within the algorithm, but it does not provide specific hyperparameter values, training configurations, or system-level settings within an experimental setup description.