On PAC-Bayes Bounds for Deep Neural Networks using the Loss Curvature
We investigate whether it's possible to tighten PAC-Bayes bounds for deep neural networks by utilizing the Hessian of the training loss at the minimum. For the case of Gaussian priors and posteriors we introduce a Hessian-based method to obtain tighter PAC-Bayes bounds that relies on closed form solutions of layerwise subproblems. We thus avoid commonly used variational inference techniques which can be difficult to implement and time consuming for modern deep architectures. We conduct a theoretical analysis that links the random initialization, minimum, and curvature at the minimum of a deep neural network to limits on what is provable about generalization through PAC-Bayes. Through careful experiments we validate our theoretical predictions and analyze the influence of the prior mean, prior covariance, posterior mean and posterior covariance on obtaining tighter bounds.
Code (0)
등록된 구현이 없습니다.
Tasks
Variational InferenceSimilar Papers 제목 키워드 기반
Information Complexity and Generalization Bounds
We present a unifying picture of PAC-Bayesian and mutual information-based upper bounds on the generalization error of randomized learning algorithms. As we show, Tong Zhang's information exponential inequality (IEI) giv…
Generalization BoundsUnderstanding Adversarially Robust Generalization via Weight-Curvature Index
Despite extensive research on adversarial examples, the underlying mechanisms of adversarially robust generalization, a critical yet challenging task for deep learning, remain largely unknown. In this work, we propose a …
Adversarial RobustnessGeneralization BoundsCR-SAM: Curvature Regularized Sharpness-Aware Minimization
The capacity to generalize to future unseen data stands as one of the utmost crucial attributes of deep neural networks. Sharpness-Aware Minimization (SAM) aims to enhance the generalizability by minimizing worst-case lo…
From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization
Curvature adaptivity is a classical theme in online optimization: for convex Lipschitz losses, adaptive methods interpolate between the optimal $O(\sqrt{T})$ regret for general convex losses and $O(\log T)$ regret under …
Misclassification excess risk bounds for PAC-Bayesian classification via convexified loss
PAC-Bayesian bounds have proven to be a valuable tool for deriving generalization bounds and for designing new learning algorithms in machine learning. However, it typically focus on providing generalization bounds with …
Generalization Bounds