Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Adversarial robustness of amortized Bayesian inference
Authors: Manuel Gloeckler, Michael Deistler, Jakob H. Macke
ICML 2023 | Venue PDF | LLM Run Details | Input Tokens: 33,457 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,679 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | 4. Experimental results. We first evaluated the robustness of Neural Posterior Estimation (NPE) and the effect of FIM-regularization on six benchmark tasks (details in Sec. A1.2). |
| Researcher Affiliation | Academia | 1Machine Learning in Science, University of T ubingen and T ubingen AI Center, T ubingen, Germany 2Max Planck Institute for Intelligent Systems, Department Empirical Inference, T ubingen, Germany. |
| Pseudocode | Yes | Algorithm 1 FIM-regularized NPE |
| Open Source Code | Yes | Code to reproduce results is available at https://github.com/mackelab/RABI. |
| Open Datasets | Yes | VAE: The decoder gĻ(x) of a Variational Autoencoder (VAE) was used as a generative model for handwritten digits (Kingma & Welling, 2014). |
| Dataset Splits | Yes | To prevent overfitting, we used early stopping based on a validation loss evaluated on 512 hold-out samples. |
| Hardware Specification | No | The paper does not specify the hardware used for running the experiments (e.g., specific GPU or CPU models, memory details). |
| Software Dependencies | No | The paper mentions "Py Torch" and "hydra" but does not provide specific version numbers for these software components. |
| Experiment Setup | Yes | We trained each model with the Adam optimizer with a learning rate of 10^-3, a batch size of 512, and a maximum of 300 epochs. |