Learning under Model Misspecification: Applications to Variational and Ensemble methods

Authors: Andres Masegosa

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments with Bayesian neural networks illustrate these findings.
Researcher Affiliation Academia Andrés R. Masegosa University of Almería andresma@ual.es
Pseudocode No The paper describes algorithms and refers to appendices for details but does not include structured pseudocode or algorithm blocks in the main text.
Open Source Code Yes The code to reproduce the results is available in https://github.com/PGM-Lab/PAC2BAYES.
Open Datasets Yes We performed the empirical evaluation on two data sets, Fashion-MNIST [58] and CIFAR-10 [30]
Dataset Splits No The paper does not explicitly provide training/validation/test split percentages or counts in the main text. It mentions 'Full details in Appendix D' but those details are not provided within the main paper's text.
Hardware Specification No No specific hardware (e.g., GPU models, CPU types, memory amounts) used for running experiments is explicitly mentioned in the paper.
Software Dependencies No No specific software dependencies with version numbers (e.g., Python 3.x, TensorFlow x.x, PyTorch x.x) are provided.
Experiment Setup No The paper mentions 'Full details in Appendix D' for the experimental setup but does not provide specific hyperparameter values or training configurations in the main text.