Adversarial robustness of amortized Bayesian inference

Authors: Manuel Gloeckler, Michael Deistler, Jakob H. Macke

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

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 gψ(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.