Interpolation and Regularization for Causal Learning
Authors: Leena Chennuru Vankadara, Luca Rendsburg, Ulrike Luxburg, Debarghya Ghoshdastidar
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Figure 2: Causal excess risk of ridge predictors based on n = 30, 000 samples from the observational distribution. Figure 4: ... Crosses indicate finite-sample risks of n = d/γ samples with d = 300. The finite risks are well-predicted by their theoretical limit. |
| Researcher Affiliation | Academia | Leena Chennuru Vankadara* University of Tübingen, Tübingen AI Center Luca Rendsburg* University of Tübingen, Tübingen AI Center Ulrike von Luxburg University of Tübingen, Tübingen AI Center Debarghya Ghoshdastidar Technical University of Munich |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The ethics review states N/A for including code, and there is no explicit statement in the paper about providing open-source code for the methodology. |
| Open Datasets | No | The paper uses synthetic data generated from its model for illustrations (e.g., 'n = 30,000 samples from the observational distribution' and 'Our synthetic datasets are generated from the model described in Eq. (1)'), but it does not provide concrete access information or links to publicly available datasets. |
| Dataset Splits | No | The paper refers to 'cross validation' and 'interventional validation set' as concepts but does not provide specific details on dataset splits (e.g., percentages or sample counts) for reproducibility of data partitioning. |
| Hardware Specification | No | The ethics review section, question 3d, states N/A regarding the total amount of compute and type of resources used, indicating no hardware specifications are provided. |
| Software Dependencies | No | The ethics review section, question 3b, states N/A regarding training details, and no specific software dependencies with version numbers are mentioned in the paper. |
| Experiment Setup | Yes | Figure 2: 'n = 30,000 samples from the observational distribution. Each model has fixed dimensions d = 300, l = 350 and SNRS = 5'. Figure 4: 'finite-sample risks of n = d/γ samples with d = 300'. |