Introducing a new framework, laplax employs Laplace approximations to improve uncertainty quantification and model selection in Bayesian neural networks.
The Laplace approximation provides a scalable and efficient means of quantifying weight-space uncertainty in deep neural networks, enabling the application of Bayesian tools such as predictive uncertainty and model selection via Occam's razor. In this work, we introduce laplax, a new open-source Python package for performing Laplace approximations with jax. Designed with a modular and purely functional architecture and minimal external dependencies, laplax offers a flexible and researcher-friendly framework for rapid prototyping and experimentation. Its goal is to facilitate research on Bayesian neural networks, uncertainty quantification for deep learning, and the development of improved Laplace approximation techniques.
No takes yet. Share an insight, caveat, or question.
Weber et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: