Stochastic Gauss-Newton Algorithms for Nonconvex Compositional Optimization

Authors: Quoc Tran-Dinh, Nhan Pham, Lam Nguyen

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

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we illustrate our theoretical results via two numerical examples on both synthetic and real datasets.
Researcher Affiliation Collaboration 1Department of Statistics and Operations Research, The University of North Carolina at Chapel Hill, NC, USA. 2IBM Research, Thomas J. Watson Research Center, NY, USA.
Pseudocode Yes Algorithm 1 (Inexact Gauss-Newton (i GN))
Open Source Code No The paper does not provide an explicit statement or link for the open-source code of the methodology described within the paper.
Open Datasets Yes We test three algorithms on four standard datasets: w8a, ijcnn1, covtype, and url combined from LIBSVM2. Further information about these dataset is described in Supp. Doc. F. Available online at https://www.csie.ntu.edu.tw/ cjlin/libsvm/
Dataset Splits No The paper mentions using standard datasets but does not explicitly provide details about training, validation, or test splits in the main text.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions using 'LIBSVM2' and 'Python codes' but does not provide specific version numbers for these or other software dependencies.
Experiment Setup Yes We use M := 1 and ρ := 1 for all datasets. We choose M := 1 and ρ := 1 for all datasets. We tune the learning rate for both N-SPIDER and SCGD and finally obtain η := 1.0 for both algorithms. We also set ε = 10 1 for N-SPIDER...