Decentralized Sum-of-Nonconvex Optimization

Authors: Zhuanghua Liu, Bryan Kian Hsiang Low

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

Reproducibility Variable Result LLM Response
Research Type Experimental The numerical experiments validate the theoretical guarantee of our proposed algorithms on both synthetic and real-world datasets. Numerical experiments on several synthetic and realworld datasets demonstrate significant improvement of our proposed PMGT-Katyusha X over existing baseline methods. To demonstrate the efficiency of PMGT-Katyusha X, we evaluate the proposed method on the sub-problem of solving PCA by the shift-and-invert method. ... We conduct our experiments on both synthetic and realworld datasets.
Researcher Affiliation Collaboration Zhuanghua Liu1, 2, Bryan Kian Hsiang Low1 1Department of Computer Science, National University of Singapore 2CNRS@CREATE LTD, 1 Create Way, #08-01 CREATE Tower, Singapore 138602
Pseudocode Yes Algorithm 1: PMGT-Katyusha X; Algorithm 2: Fast Mix(x0, M, W)
Open Source Code No The paper does not provide any explicit statements about making its source code open or providing a link to a code repository.
Open Datasets Yes For the real-world dataset, we use the Covtype downloaded from the LIBSVM website2. 2https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets
Dataset Splits No The paper does not explicitly provide training/validation/test dataset splits. It describes an optimization problem evaluated on given datasets.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU, GPU models, or memory specifications) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies, libraries, or solvers with version numbers.
Experiment Setup Yes The left column represents results with the ratio r = 2 and the right column represents results with the ratio r = 300 defined in Problem (3). ... The gossip matrix W underlying the decentralized network... The second largest eigenvalue of the resulting matrix is λ2(W) = 0.97.