Identifying Representations for Intervention Extrapolation

Authors: Sorawit Saengkyongam, Elan Rosenfeld, Pradeep Kumar Ravikumar, Niklas Pfister, Jonas Peters

ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We validate our theoretical findings through a series of synthetic experiments and show that our approach can indeed succeed in predicting the effects of unseen interventions. and 6 EXPERIMENTS We now conduct simulation experiments to empirically validate our theoretical findings.
Researcher Affiliation Academia 1ETH Zürich 2Carnegie Mellon University 3University of Copenhagen
Pseudocode Yes Algorithm 1: An algorithm for Rep4Ex
Open Source Code Yes The code for all experiments is included in the supplementary material.
Open Datasets No The paper uses data generated from defined Structural Causal Models (SCMs) for its experiments (e.g., S(α) and S(γ)), which are synthetic. No concrete access information or citation to a public dataset is provided.
Dataset Splits No The paper mentions 'training support' and generating '100 test points' for some experiments, but does not provide specific train/validation/test split percentages or sample counts for the main experiments.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory specifications) used for running the experiments.
Software Dependencies No The paper mentions software components like 'neural networks', 'Adam optimizer', and 'Leaky ReLU activation functions', but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes Learning rate: 0.005 Batch size: 256 Optimizer: Adam optimizer with β1 = 0.9, β2 = 0.999 Number of epochs: 1000. and Architecture: three hidden layers with the hidden size of 32