BayesIMP: Uncertainty Quantification for Causal Data Fusion

Authors: Siu Lun Chau, Jean-Francois Ton, Javier González, Yee Teh, Dino Sejdinovic

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To demonstrate the utility of our uncertainty estimation, we apply our method to the Causal Bayesian Optimisation task and show improvements over state-of-the-art methods.
Researcher Affiliation Collaboration Siu Lun Chau University of Oxford Jean-François Ton University of Oxford Javier González Microsoft Research Cambridge Yee Whye Teh University of Oxford Dino Sejdinovic University of Oxford
Pseudocode No The paper describes algorithms verbally and mathematically but does not include a structured pseudocode or algorithm block.
Open Source Code No The paper does not contain any explicit statement about open-sourcing the code or a link to a code repository.
Open Datasets Yes On one hand we have observational data, from one medical study D1 [6], describing the causal relationship between statin level and prostate specific antigen (PSA), and on the other hand we have observational data, from a second study D2 [7], that looked into the link between PSA level and prostate cancer volume.
Dataset Splits No The paper mentions "N = 100 datapoints for D1 and M = 50 datapoints D2." and "In Fig.5 we plot the mean and the 95% credible interval of the resulting GP models for E[T|do(X) = x]." However, it does not explicitly provide training/validation/test splits.
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments (e.g., GPU/CPU models, memory specifications).
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., 'Python 3.8', 'PyTorch 1.9').
Experiment Setup No The paper mentions general experimental settings like using the 'expected improvement (EI) acquisition function' and that 'The data generation and details were added in the Appendix', but it does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or detailed training configurations in the main text.