Selective Inference for Sparse High-Order Interaction Models

Authors: Shinya Suzumura, Kazuya Nakagawa, Yuta Umezu, Koji Tsuda, Ichiro Takeuchi

ICML 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the effectiveness of the proposed methods through numerical experiments both on synthetic and real datasets.
Researcher Affiliation Academia 1Nagoya Institute of Technology, Nagoya, Japan 2University of Tokyo, Tokyo, Japan 3RIKEN, Tokyo, Japan.
Pseudocode No The paper describes algorithmic steps and theorems but does not include a clearly labeled pseudocode block or algorithm section.
Open Source Code No The paper does not provide any specific statement or link indicating that the source code for the methodology is openly available.
Open Datasets Yes We applied the selective inference approach to HIV-1 sequence data obtained from Stanford HIV Drug Resistance Database (Rhee et al., 2003).
Dataset Splits No The paper discusses data splitting as a comparative baseline method ('split' approach) but does not provide specific train/validation/test dataset splits or percentages for the reproduction of its own model training and evaluation.
Hardware Specification No The paper does not specify the hardware used for running the experiments (e.g., CPU, GPU models, or memory specifications).
Software Dependencies No The paper does not mention specific software names with version numbers that would be necessary for reproduction.
Experiment Setup Yes We set the baseline parameters as n = 100, d = 100, k = 5, r = 5, α = 0.05, σ = 0.5, and ζ = 0.6.