Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers

Authors: Yuxing Liu, Lesi Chen, Luo Luo

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We further perform numerical experiments to validate the advantage of our method. In this section, we provide the numerical experiments to compare the performance of CESAR with baseline methods Mudag (Ye et al., 2023), Acc-VR-EXTRA and Acc-VR-DIGING (Li et al., 2022a). We conduct our experiments on datasets a9a and w6a (Chang & Lin, 2011).
Researcher Affiliation Academia 1School of Data Science, Fudan University, Shanghai, China 2Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China 3 Shanghai Key Laboratory for Contemporary Applied Mathematics, Shanghai, China. Correspondence to: Luo Luo <luoluo@fudan.edu.cn>.
Pseudocode Yes Algorithm 2 CESAR
Open Source Code No The paper does not provide any specific link or statement indicating that the source code for CESAR is publicly available.
Open Datasets Yes We conduct our experiments on datasets a9a and w6a (Chang & Lin, 2011).
Dataset Splits No The paper mentions using datasets for experiments but does not explicitly detail the train/validation/test splits, percentages, or absolute counts for reproducibility.
Hardware Specification No The paper does not specify the hardware used to run the experiments (e.g., GPU models, CPU types, or cloud instances).
Software Dependencies No The paper does not provide specific version numbers for any software dependencies used in the experiments.
Experiment Setup Yes We set the mixing matrix W to be associated with a random graph that each edge is connected with probability 1/30, which leads to 1 λ2(W) 0.0382. The condition numbers in our problem are listed in Table 3.