Papers › Efficient Bayesian Updates for Deep Learning via Laplace Approximations

Efficient Bayesian Updates for Deep Learning via Laplace Approximations

12 Oct 2022arXiv:2210.06112archive 2025-07-28

Denis Huseljic, Marek Herde, Lukas Rauch, Paul Hahn, Zhixin Huang, Daniel Kottke, Stephan Vogt, Bernhard Sick

Since training deep neural networks takes significant computational resources, extending the training dataset with new data is difficult, as it typically requires complete retraining. Moreover, specific applications do not allow costly retraining due to time or computational constraints. We address this issue by proposing a novel Bayesian update method for deep neural networks by using a last-layer Laplace approximation. Concretely, we leverage second-order optimization techniques on the Gaussian posterior distribution of a Laplace approximation, computing the inverse Hessian matrix in closed form. This way, our method allows for fast and effective updates upon the arrival of new data in a stationary setting. A large-scale evaluation study across different data modalities confirms that our updates are a fast and competitive alternative to costly retraining. Furthermore, we demonstrate its applicability in a deep active learning scenario by using our update to improve existing selection strategies.

PaperPDFCode

Code

dhuseljic/dal-toolbox officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Active LearningDeep Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DropoutGaussian Process

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections