Do Subsampled Newton Methods Work for High-Dimensional Data?

Authors: Xiang Li, Shusen Wang, Zhihua Zhang4723-4730

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

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper theoretically justifies the effectiveness of subsampled Newton methods on strongly convex empirical risk minimization with high dimensional data.
Researcher Affiliation Academia Xiang Li,1 Shusen Wang,2 Zhihua Zhang1,3 1School of Mathematical Sciences, Peking University, China 2Department of Computer Science, Stevens Institute of Technology, USA 3National Engineering Lab for Big Data Analysis and Applications, Peking University, China
Pseudocode No The paper includes 'Algorithm description' sections for SSN, GIANT, and SSPN, but these are prose descriptions of the procedures rather than structured pseudocode blocks or formally labeled algorithms.
Open Source Code No The paper does not provide any statement or link indicating that source code for the described methodology is publicly available.
Open Datasets No The paper is theoretical and does not involve experiments with datasets, thus no information about public datasets is provided.
Dataset Splits No The paper is theoretical and does not involve experiments with datasets, thus no information about dataset splits for validation is provided.
Hardware Specification No The paper is theoretical and does not describe experimental hardware specifications.
Software Dependencies No The paper is theoretical and does not specify software dependencies with version numbers for experimental reproducibility.
Experiment Setup No The paper is theoretical and does not provide specific experimental setup details, hyperparameters, or training configurations.