DRCFS: Doubly Robust Causal Feature Selection

Authors: Francesco Quinzan, Ashkan Soleymani, Patrick Jaillet, Cristian R. Rojas, Stefan Bauer

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We perform extensive experiments across a wide range of simulated and semisynthetic datasets.
Researcher Affiliation Academia 1Department of Computer Science, University of Oxford 2Laboratory for Information & Decision Systems (LIDS), Massachusetts Institute of Technology 3KTH Royal Institute of Technology 4TU Munich 5Helmholtz Munich.
Pseudocode Yes Algorithm 1 Doubly Robust Causal Feature Selection Algorithm (DRCFS)
Open Source Code No The paper mentions external R packages used for baselines but does not provide a specific repository link or an explicit statement about the availability of the source code for their proposed method (DRCFS).
Open Datasets Yes In this part, to assess the performance of our algorithm with a taste of real-world application, we conduct a semi-synthetic experiment based on microbiome abundance data in plant leaves from Regalado et al. (2020).
Dataset Splits Yes split the n samples D = {(x1i, . . . , xmi, yi)}i=1,...,n into k disjoint sets D1, . . . , Dk; define Dc l D \ Dl for all l [k];
Hardware Specification No The paper does not provide any specific hardware details such as GPU models, CPU types, or memory used for running the experiments.
Software Dependencies No The paper mentions the use of 'R Packages "Compare Causal Networks"' and '"selective Inference: Tools for Post-Selection Inference"' for baselines, and 'Forest Riesz' for estimation, but does not provide specific version numbers for these or any other software dependencies crucial for replication.
Experiment Setup Yes Algorithm 1 Doubly Robust Causal Feature Selection Algorithm (DRCFS)... split the n samples D = {(x1i, . . . , xmi, yi)}i=1,...,n into k disjoint sets D1, . . . , Dk;