Efficient Symmetric Norm Regression via Linear Sketching

Authors: Zhao Song, Ruosong Wang, Lin Yang, Hongyang Zhang, Peilin Zhong

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

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical Evaluation. In Section E of the supplementary material, we test our algorithms on real datasets. Our empirical results quite clearly demonstrate the practicality of our methods.
Researcher Affiliation Academia Zhao Song University of Washington, Ruosong Wang Carnegie Mellon University, Lin F. Yang University of California, Los Angeles, Hongyang Zhang Toyota Technological Institute at Chicago, Peilin Zhong Columbia University
Pseudocode Yes Figure 1: Algorithm for Orlicz norm regression
Open Source Code No The paper states that empirical evaluation was performed (Section E of supplementary material) but does not provide any explicit statement about releasing the source code for the described methodology or a link to a code repository.
Open Datasets No The paper mentions testing algorithms on 'real datasets' in Section E of the supplementary material, but does not specify the datasets or provide concrete access information (link, DOI, citation with authors/year, or specific names of well-known public datasets) in the main paper.
Dataset Splits No The paper does not provide specific details on training, validation, or test dataset splits, percentages, or sample counts.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., CPU/GPU models, memory) used to run the experiments.
Software Dependencies No The paper does not provide specific software dependency details, such as library names with version numbers, needed to replicate the experiments.
Experiment Setup No The paper does not provide specific experimental setup details, such as concrete hyperparameter values, training configurations, or system-level settings, in the main text.