Analyzing Deep PAC-Bayesian Learning with Neural Tangent Kernel: Convergence, Analytic Generalization Bound, and Efficient Hyperparameter Selection

Published: 30 May 2023, Last Modified: 17 Sept 2024Accepted by TMLREveryoneRevisionsBibTeXCC BY 4.0
Abstract: PAC-Bayes is a well-established framework for analyzing generalization performance in machine learning models. This framework provides a bound on the expected population error by considering the sum of training error and the divergence between posterior and prior distributions. In addition to being a successful generalization bound analysis tool, the PAC-Bayesian bound can also be incorporated into an objective function for training probabilistic neural networks, which we refer to simply as {\it Deep PAC-Bayesian Learning}. Deep PAC-Bayesian learning has been shown to achieve competitive expected test set error and provide a tight generalization bound in practice at the same time through gradient descent training. Despite its empirical success, theoretical analysis of deep PAC-Bayesian learning for neural networks is rarely explored. To this end, this paper proposes a theoretical convergence and generalization analysis for Deep PAC-Bayesian learning. For a deep and wide probabilistic neural network, our analysis shows that PAC-Bayesian learning corresponds to solving a kernel ridge regression when the probabilistic neural tangent kernel (PNTK) is used as the kernel. We utilize this outcome in conjunction with the PAC-Bayes $\mathcal{C}$-bound, enabling us to derive an analytical and guaranteed PAC-Bayesian generalization bound for the first time. Finally, drawing insight from our theoretical results, we propose a proxy measure for efficient hyperparameter selection, which is proven to be time-saving on various benchmarks. Our work not only provides a better understanding of the theoretical underpinnings of Deep PAC-Bayesian learning, but also offers practical tools for improving the training and generalization performance of these models.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: First round changes (mainly according to comments by Reviewer Q6fj and Reviewer PSU9) are marked in blue. Second round changes (mainly according to comments by Reviewer c5C9 and Reviewer 4k6L are marked in red. Third round changes are marked in purple. Final changes: capitalise all words that require it, replace the Arxiv version with the published version. Finally, we would like to thank the reviewers and the action editor for taking time and providing us with the helpful feedback.
Supplementary Material: zip
Assigned Action Editor: ~Benjamin_Guedj1
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Number: 916
Loading