Identifiable Latent Polynomial Causal Models through the Lens of Change
Authors: Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong, Biwei Huang, Anton van den Hengel, Kun Zhang, Javen Qinfeng Shi
ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our experimental results, obtained from both synthetic and real-world data, validate our theoretical contributions concerning identifiability and consistency. |
| Researcher Affiliation | Academia | 1 Australian Institute for Machine Learning, The University of Adelaide, Australia 2 School of Computer Science and Engineering, The University of New South Wales, Australia 3 School of Mathematics and Statistics, The University of Melbourne, Australia 4 Halicio glu Data Science Institute (HDSI), University of California San Diego, USA 5 Department of Philosophy, Carnegie Mellon University, USA 6 Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates |
| Pseudocode | No | Figure 8 depicts the proposed method to learn polynomial causal representations with non-Gaussian noise. Figure 9 depicts the proposed method to learn polynomial causal representations with Gaussian noise. |
| Open Source Code | No | The paper does not contain any explicit statement about releasing code or a link to a repository. |
| Open Datasets | Yes | Image Data We further verify the proposed identifiability results and method on images from the chemistry dataset proposed in Ke et al. (2021)... |
| Dataset Splits | No | Synthetic Data We first conduct experiments on synthetic data, generated by the following process: we divide latent noise variables into M segments, where each segment corresponds to one value of u as the segment label. Within each segment, the location and scale parameters are respectively sampled from uniform priors. |
| Hardware Specification | No | The paper does not provide any specific hardware details used for running the experiments. |
| Software Dependencies | No | Instead, we straightforwardly use the Py Torch (Paszke et al., 2017) implementation of the method of Jankowiak & Obermeyer (2018), which computes implicit reparameterization using a closed-form approximation of the probability density function derivative. |
| Experiment Setup | Yes | For experiments on the synthetic data and f MRI data, the encoder, decoder, MLP for λ, and MLP for prior are implemented by using 3-layer fully connected networks and Leaky-Re LU activation functions. For optimization, we use Adam optimizer with learning rate 0.001. |