Smoothness-Based Derandomization of PAC-Bayes Bounds
Alexandre Lemire Paquin, Brahim Chaib-Draa, Philippe Giguère
cs.LG, stat.ML
Submitted: 2026-06-17
Comments: 49 pages, 8 figures, 3 tables. Version 2 adds the SHEL network specialization and experiments on MNIST
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- De-randomized PAC-Bayes Margin Bounds: Applications to Non-convex and Non-smooth Predictors
- Generalizing and Improving Jacobian and Hessian Regularization
- PAC-Bayes unleashed: generalisation bounds with unbounded losses
- A Framework for Bounding Deterministic Risk with PAC-Bayes: Applications to Majority Votes
- Regularizing Deep Neural Networks with Stochastic Estimators of Hessian Trace
- A vector-contraction inequality for Rademacher complexities
- A White Paper on Neural Network Quantization
- PAC-Bayes Analysis Beyond the Usual Bounds
- An Exploration into why Output Regularization Mitigates Label Noise
- Gradient Regularization Improves Accuracy of Discriminative Models
- A General Framework for the Practical Disintegration of PAC-Bayesian Bounds
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks