Triad Constraints for Learning Causal Structure of Latent Variables
Authors: Ruichu Cai, Feng Xie, Clark Glymour, Zhifeng Hao, Kun Zhang
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on both synthetic and real data demonstrate the effectiveness and reliability of our method. |
| Researcher Affiliation | Academia | 1 School of Computer Science, Guangdong University of Technology, Guangzhou, China 2 Department of Philosophy, Carnegie Mellon University, Pittsburgh, USA 3 School of Mathematics and Big Data, Foshan University, Foshan, China |
| Pseudocode | Yes | Algorithm 1 Find Clusters; Algorithm 2 Learn Latent Structure |
| Open Source Code | No | The paper mentions using implementations from the TETRAD package for comparison ("We used these implementations in the TETRAD package, which can be downloaded at http://www.phil.cmu. edu/tetrad/"), but it does not provide open-source code for its own proposed methodology (LSTC). |
| Open Datasets | No | The paper uses synthetic data and Hong Kong stock market data. For synthetic data, it describes how it was generated but does not provide access. For the Hong Kong stock market data, it states "The data set contains 1331 daily returns of 14 major stocks" and cites a paper ([Zhang and Chan, 2008]) that *used* the data, but does not provide a direct link, DOI, or repository for *this specific dataset* as used in their experiments. No concrete access information is given for either dataset. |
| Dataset Splits | No | The paper mentions sample sizes selected from {500, 1000, 2000} for synthetic data and discusses evaluation metrics such as F1 score, latent omission, and latent commission. However, it does not explicitly provide details about train/validation/test splits, such as specific percentages or counts for each partition. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used to run the experiments, such as GPU/CPU models, memory, or cloud computing specifications. |
| Software Dependencies | No | The paper mentions the "Hilbert-Schmidt Independence Criterion (HSIC) test [Gretton et al., 2008]" and using "implementations in the TETRAD package." However, it does not provide specific version numbers for any software dependencies used in their own implementation, such as programming languages or libraries. |
| Experiment Setup | Yes | In all four cases, the causal strength b is sampled from a uniform distribution between [ 2, 0.5] [0.5, 2], noise terms are generated as the fifth power of uniform(-1,1) variables, and the sample size is selected from {500, 1000, 2000}. ... The kernel width in the HSIC test [Gretton et al., 2008] is set to 0.1. |