On the Laplace approximation for sequential model selection of Bayesian neural networks


Loading...

Author / Producer

Date

2022

Publication Type

Master Thesis

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

The Laplace approximation yields a tractable marginal likelihood for Bayesian neural networks. This enables empirical Bayes methods for optimizing BNN hyperparameters directly on training data, even if validation data is unavailable. Sequential decision-making problems are typical instances of settings that rely on training data alone. Hence, this thesis asks whether hyperparameter optimization using the Laplace marginal likelihood benefits Bayesian neural networks on sequential decision-making problems. The answer is mixed: while online model selection improves decision-making performance for large sample sizes, maximum marginal likelihood models in the small-data regime behave like constant predictors. Therefore, this thesis further investigates the relation between the Laplace marginal likelihood and generalization. Towards an explanation, we hypothesize that the marginal likelihood assesses generalization in observation space, while decision-making requires generalization in function space. In particular, fixed hyperparameters yield overfitting in function space, while optimized hyperparameters yield underfitting. Lastly, we hypothesize that implicit ensembling effects during sequential decision-making compensate overfitting, but not underfitting.

Publication status

published

External links

Editor

Contributors

Examiner : Fortuin, Vincent
Examiner: Rätsch, Gunnar

Book title

Journal / series

Volume

Pages / Article No.

Publisher

ETH Zurich

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

09568 - Rätsch, Gunnar / Rätsch, Gunnar check_circle

Notes

Funding

Related publications and datasets