Selective inference for group-sparse linear models

Authors: Fan Yang, Rina Foygel Barber, Prateek Jain, John Lafferty

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We give numerical results to illustrate these tools on simulated data and on health record data. In this section we present results from experiments on simulated and real data, performed in R [11].
Researcher Affiliation Collaboration Fan Yang Department of Statistics University of Chicago fyang1@uchicago.edu Rina Foygel Barber Department of Statistics University of Chicago rina@uchicago.edu Prateek Jain Microsoft Research India prajain@microsoft.com John Lafferty Depts. of Statistics and Computer Science University of Chicago lafferty@galton.uchicago.edu
Pseudocode Yes See the supplementary material for detailed pseudo-code.
Open Source Code Yes Code reproducing experiments: http://www.stat.uchicago.edu/~rina/group_inf.html
Open Datasets Yes We examine the 2015 California county health data7 which was also studied by Loftus and Taylor [9]. ... 7Available at http://www.countyhealthrankings.org
Dataset Splits No The paper describes generating simulated data and using real-world data but does not specify explicit train/validation/test splits, percentages, or cross-validation details for reproducibility.
Hardware Specification No The paper does not provide specific hardware details such as GPU or CPU models, memory specifications, or cloud instance types used for running experiments.
Software Dependencies No The paper only mentions 'performed in R [11]' without specifying versions of R or any other software libraries or packages with their version numbers.
Experiment Setup Yes We run IHT to select k = 10 groups over T = 5 iterations, with step sizes ηt = 2 and initial point β0 = 0.