Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?
Abstract
A major challenge in sample-based inference (SBI) for Bayesian neural networks is the size and structure of the networks’ parameter space. Our work shows that successful SBI is possible by embracing the characteristic relationship between weight and function space, uncovering a systematic link between overparameterization and the difficulty of the sampling problem. Through extensive experiments, we establish practical guidelines for sampling and convergence diagnosis. As a result, we present a deep ensemble initialized approach as an effective solution with competitive performance and uncertainty quantification.
Cite
Text
Sommer et al. "Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?." International Conference on Machine Learning, 2024.Markdown
[Sommer et al. "Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?." International Conference on Machine Learning, 2024.](https://mlanthology.org/icml/2024/sommer2024icml-connecting/)BibTeX
@inproceedings{sommer2024icml-connecting,
title = {{Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?}},
author = {Sommer, Emanuel and Wimmer, Lisa and Papamarkou, Theodore and Bothmann, Ludwig and Bischl, Bernd and Rügamer, David},
booktitle = {International Conference on Machine Learning},
year = {2024},
pages = {45988-46018},
volume = {235},
url = {https://mlanthology.org/icml/2024/sommer2024icml-connecting/}
}