A Sharper Generalization Bound for Divide-and-Conquer Ridge Regression

Authors: Shusen Wang5305-5312

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Since extensive empirical studies of the DC method have been conducted by (Zhang, Duchi, and Wainwright 2013; Wang, Gittens, and Mahoney 2018), we focus on the theory without conducting experiments.
Researcher Affiliation Academia Shusen Wang Department of Computer Science, Stevens Institute of Technology shusen.wang@stevens.edu
Pseudocode No The paper focuses on theoretical analysis and proofs and does not include any sections or figures explicitly labeled 'Pseudocode' or 'Algorithm'.
Open Source Code No The authors state, 'we focus on the theory without conducting experiments,' implying that no new code for the methodology described in this paper was developed or released.
Open Datasets No The paper states, 'we focus on the theory without conducting experiments,' indicating that no empirical evaluations were performed using a dataset.
Dataset Splits No The paper is theoretical and states, 'we focus on the theory without conducting experiments,' so no dataset splits for training, validation, or testing are provided.
Hardware Specification No The paper states, 'we focus on the theory without conducting experiments,' and thus does not provide any hardware specifications for experimental runs.
Software Dependencies No The paper explicitly states, 'we focus on the theory without conducting experiments,' and consequently does not list specific software dependencies with version numbers.
Experiment Setup No The paper explicitly states, 'we focus on the theory without conducting experiments,' and therefore does not describe any experimental setup details such as hyperparameters or training configurations.