mlsanityData to 14 Oct 2026

laplax -- Laplace Approximations with JAX

arXiv 2507.17013 ↗First posted 22 Jul 2025cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 22 of its 32 references that are in the map. First posted on arXiv 22 Jul 2025.

Builds on

22 of 32 references.

References · 22

  1. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 365
  2. 2020Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networkscited by 231
  3. 2018Online Structured Laplace Approximations For Overcoming Catastrophic Forgettingcited by 201
  4. 2019Functional Variational Bayesian Neural Networkscited by 127
  5. 2021Scalable Marginal Likelihood Estimation for Model Selection in Deep Learningcited by 106
  6. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  7. 2020Bayesian Deep Learning via Subnetwork Inferencecited by 87
  8. 2024Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Taskscited by 78
  9. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 62
  10. 2020All You Need is a Good Functional Prior for Bayesian Deep Learningcited by 61
  11. 2023The LLM Surgeoncited by 38
  12. 2020Fast Predictive Uncertainty for Classification with Bayesian Deep Networkscited by 31
10 more
  1. 2020Learnable Uncertainty under Laplace Approximationscited by 29
  2. 2021Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learningcited by 25
  3. 2023Learning Layer-wise Equivariances Automatically using Gradientscited by 23
  4. 2024Reparameterization invariance in approximate Bayesian inferencecited by 17
  5. 2020Mean-Field Approximation to Gaussian-Softmax Integral with Application to Uncertainty Estimationcited by 16
  6. 2024Linearization Turns Neural Operators into Function-Valued Gaussian Processescited by 12
  7. 2024FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learningcited by 11
  8. 2023Promises and Pitfalls of the Linearized Laplace in Bayesian Optimizationcited by 10
  9. 2025Position: Curvature Matrices Should Be Democratized via Linear Operatorscited by 9
  10. 2024Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihoodcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Richer Bayesian Last Layers with Subsampled NTK Featurescited by 4
  2. 2026Efficient Credal Prediction through Decalibrationcited by 1
  3. 2026A Ground-Truth Framework for Uncertainty Disentanglement with Posterior Riskcited by 1
  4. 2026VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learningcited by 0
  5. 2026Subspace Inference Enables Efficient Active Reward Learning from Preferencescited by 0