Aggregation of Multiple Knockoffs
Authors: Tuan-Binh Nguyen, Jerome-Alexis Chevalier, Bertrand Thirion, Sylvain Arlot
ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We provide a new inference procedure, prove its core properties, and demonstrate its benefits in a set of experiments on synthetic and real datasets. |
| Researcher Affiliation | Academia | 1Universit e Paris-Saclay, CNRS, Inria, Laboratoire de math ematiques d Orsay, 91405, Orsay, France 2Inria, CEA, Universit e Paris-Saclay, France. |
| Pseudocode | Yes | Algorithm 1 AKO Aggregation of multiple knockoffs |
| Open Source Code | No | The paper does not provide any explicit statement or link indicating that the source code for the described methodology is openly available. |
| Open Datasets | Yes | To test AKO on real datasets, we first perform a genomewide association study (GWAS) on genomic data. The aim is to detect association of each of 174 candidate genes with a phenotype FT GH that describes flowering time of Arabidopsis thaliana, first done by Atwell et al. (2010). ... Human Connectome Project (HCP900) is a collection of neuroimaging and behavioral data on 900 healthy young adults, aged 22 35. |
| Dataset Splits | No | The paper describes the setup for synthetic data and lists dimensions for real datasets, but it does not explicitly provide information on how these datasets were split into training, validation, and test sets, nor does it specify a cross-validation scheme. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments. |
| Software Dependencies | No | The paper does not list specific software dependencies with their version numbers required to reproduce the experiments. |
| Experiment Setup | Yes | Simulation Setup. Our first experiment is a simulation scenario where a design matrix X (n = 500, p = 1000) with its continuous response vector y are created following a linear model assumption. ... The three main parameters controlling this simulation are correlation ρ, sparsity degree k and signal-to-noise ratio SNR. ... In the experiments, we fix γ = 0.3 and B = 25. |