Work

Bayesian Posterior Approximation With Stochastic Ensembles

Year: 2023

Type: conference-paper

Abstract: We introduce ensembles of stochastic neural networks to approximate the Bayesian posterior, combining stochastic methods such as dropout with deep ensembles. The stochas-tic ensembles are formulated as families of distributions and trained to approximate the Bayesian posterior with variational inference. We implement stochastic ensembles based on Monte Carlo dropout, DropConnect and a novel non-parametric version of dropout and evaluate them on a toy problem and CIFAR image classification. For both tasks, we test the quality of the posteriors directly against Hamil-tonian Monte Carlo simulations. Our results show that stochastic ensembles provide more accurate posterior esti-mates than other popular baselines for Bayesian inference.

Source: IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI: 10.1109/cvpr52729.2023.01317

Authors: Oleksandr Balabanov, Bernhard Mehlig, Hampus Linander

Institutions: Stockholm University, University of Gothenburg, Chalmers University of Technology

Language: English

Topic: Gaussian Processes and Bayesian Inference

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Knut och Alice Wallenbergs Stiftelse, Vetenskapsrådet

Awards: Entanglement and symmetries in topological phases of matter, G6514098083