Laplace Redux -- Effortless Bayesian Deep Learning

Abstract

Bayesian formulations of deep learning have been shown to have compelling theoretical properties and offer practical functional benefits, such as improved predictive uncertainty quantification and model selection. The Laplace approximation (LA) is a classic, and arguably the simplest family of approximations for the intractable posteriors of deep neural networks. Yet, despite its simplicity, the LA is not as popular as alternatives like variational Bayes or deep ensembles. This may be due to assumptions that the LA is expensive due to the involved Hessian computation, that it is difficult to implement, or that it yields inferior results. In this work we show that these are misconceptions: we (i) review the range of variants of the LA including versions with minimal cost overhead; (ii) introduce "laplace", an easy-to-use software library for PyTorch offering user-friendly access to all major flavors of the LA; and (iii) demonstrate through extensive experiments that the LA is competitive with more popular alternatives in terms of performance, while excelling in terms of computational cost. We hope that this work will serve as a catalyst to a wider adoption of the LA in practical deep learning, including in domains where Bayesian approaches are not typically considered at the moment.

NeurIPS 2021 camera-ready version; source code: https://github.com/AlexImmer/Laplace

References in corpus (11)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• On Calibration of Modern Neural Networks
• Scalable Bayesian Optimization Using Deep Neural Networks
• WILDS: A Benchmark of in-the-Wild Distribution Shifts
• What Are Bayesian Neural Network Posteriors Really Like?
• Practical Gauss-Newton Optimisation for Deep Learning
• 'In-Between' Uncertainty in Bayesian Neural Networks
• Subspace Inference for Bayesian Deep Learning
• Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks
• Bayesian Optimization Meets Laplace Approximation for Robotic Introspection
• Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning

Cited by in corpus (3)

• Bayesian Deep Learning via Subnetwork Inference
• Ranking over Regression for Bayesian Optimization and Molecule Selection
• Efficient Online Bayesian Inference for Neural Bandits