========================================================================================================
- The code is for the methods described in
Xianghui Mao, Kun Yuan, Yubin Hu, Yuantao Gu, Ali H. Sayed and Wotao Yin "Walkman: A Communication-Efficient Random-Walk Algorithm for Decentralized Optimization", arXiv:1804.06568 Version 1.0 Copyright(c) 2019 Xianghui Mao, Kun Yuan, Yubin Hu, Yuantao Gu, Ali H. Sayed and Wotao Yin All Rights Reserved.
========================================================================================================
- Experiment List
-
least_squares Experiments on solving least squares problem, corresponding to Section VI.A of the paper. a. Run least_squares/ls_main.m to get Fig.2
-
logistic_regression Experiments on solving sparse logistic regression problem, corresponding to Section VI.B of the paper. a. Run logistic_regression/lr_l1sparse.m to get Fig.3
-
NN_PCA Experiment on solving non-negative principal component analysis problem, corresponding to Section VI.C of the paper. a. Run NN_PCA/NN_PCA.m to get Fig.4
======================================================================================================== For any problems with the code, please contact us: maoxh14@mails.tsinghua.edu.cn, kunyuan@ucla.edu, hu-yb16@mails.tsinghua.edu.cn, gyt@tsinghua.edu.cn, ali.sayed@epfl.ch, wotaoyin@math.ucla.edu