Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks

Dominik Schnaus, Jongseok Lee, Daniel Cremers, Rudolph Triebel

Research output: Contribution to journalConference articlepeer-review


In this work, we propose a novel prior learning method for advancing generalization and uncertainty estimation in deep neural networks. The key idea is to exploit scalable and structured posteriors of neural networks as informative priors with generalization guarantees. Our learned priors provide expressive probabilistic representations at large scale, like Bayesian counterparts of pretrained models on ImageNet, and further produce non-vacuous generalization bounds. We also extend this idea to a continual learning framework, where the favorable properties of our priors are desirable. Major enablers are our technical contributions: (1) the sums-of-Kronecker-product computations, and (2) the derivations and optimizations of tractable objectives that lead to improved generalization bounds. Empirically, we exhaustively show the effectiveness of this method for uncertainty estimation and generalization.

Original languageEnglish
Pages (from-to)30252-30284
Number of pages33
JournalProceedings of Machine Learning Research
StatePublished - 2023
Event40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: 23 Jul 202329 Jul 2023


Dive into the research topics of 'Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks'. Together they form a unique fingerprint.

Cite this