We consider a PAC-Bayes type learning rule for binary classification, balancing the training error of a randomized ''posterior'' predictor with its KL divergence to a pre-specified ''prior''. This can be seen as an extension of a modified two-part-code Minimum Description Length (MDL) learning rule, to continuous priors and randomized predictions. With a balancing parameter of λ=1 this learning rule recovers an (empirical) Bayes posterior and a modified variant recovers the profile posterior, linking with standard Bayesian prediction (up to the treatment of the single-parameter noise level). However, from a risk-minimization prediction perspective, this Bayesian predictor overfits and can lead to non-vanishing excess loss in the agnostic case. Instead a choice of λ≫1, which can be seen as using a sample-size-dependent-prior, ensures uniformly vanishing excess loss even in the agnostic case. We precisely characterize the effect of under-regularizing (and over-regularizing) as a function of the balance parameter λ, understanding the regimes in which this under-regularization is tempered or catastrophic. This work extends previous work by Zhu and Srebro [2025] that considered only discrete priors to PAC Bayes type learning rules and, through their rigorous Bayesian interpretation, to Bayesian prediction more generally.
Figures & tables
Figure 1: The function ℓλ(L∗) of equation ( 6 ). When the PAC-Bayes rule is used with a fixed λ , the corresponding curve describes the best possible worst-case guarantee on the limiting error, across agnostic noise levels L∗ . The curves are always above the diagonal (overfitting), but approach it as λ→∞ , which is necessary for consistency (learning). For λ≥1 , the overfitting is “tempered”, meaning that the limiting error is less than 21 (better than chance). For λ<1 , this is only the case for L∗<H−1(λ) , indicated by blue dots. For λ=0 the overfitting can be catastrophic, with worst case limiting error always 1 . [Reproduced with permission from Zhu and Srebro (2025) .]
PAC-Bayes theory provides generalization guarantees by controlling the Kullback--Leibler (KL) divergence between posterior and prior distributions over a chosen hypothesis representation. However, predictive risk depends only on the predictive behavior induced by a hypothesis, not on the particular internal realization that implements that behavior. In over-parameterized systems, many distinct configurations induce identical predictive behavior, yet the classical PAC-Bayes KL divergence does not distinguish uncertainty over predictive behavior from variation among behaviorally equivalent realizations. We show that this distinction induces an exact structural decomposition of classical PAC-Bayes complexity. We formalize behavioral equivalence through a measurable behavior map and use measure disintegration to decompose probability measures on the configuration space into a distribution over predictive behaviors and conditional distributions over behavioral fibers. This yields an exact decomposition of the classical PAC-Bayes KL divergence into a behavior-selection term and a realization-level term given by an expected conditional KL within fibers. We define Z-information as the negative of this realization-level contribution: the exact gap between the KL divergence and the complexity of uncertainty over predictive behavior alone. We further show that the behavior-selection term admits an exact variational characterization: it is the minimum KL divergence among all posteriors inducing the same distribution over predictive behaviors, attained by a canonical fiber-symmetrized representative. Finally, we show that symmetry, behavior-preserving directions, fiber geometry, and invariance under fiber-preserving perturbations arise naturally from the same behavior-map structure. Together, these results identify predictive behavior as the natural object of PAC-Bayes complexity.
Vasant G. Honavar, Satish Kumar Keshri, Neil Ashtekar +1
Artificial Intelligence Research Laboratory Department of Informatics and Intelligent Systems The Pennsylvania State University · Artificial Intelligence Research Laboratory Department of Computer Science and Engineering The Pennsylvania State University
We derive explicit non-asymptotic PAC-Bayes generalization bounds for Gibbs posteriors, that is, data-dependent distributions over model parameters obtained by exponentially tilting a prior with the empirical risk. Unlike classical worst-case complexity bounds based on uniform laws of large numbers, which require explicit control of the model space in terms of metric entropy (integrals), our analysis yields posterior-averaged risk bounds that can be applied to overparameterized models and adapt to the data structure and the intrinsic model complexity. The bound involves a marginal-type integral over the parameter space, which we analyze using tools from singular learning theory to obtain explicit and practically meaningful characterizations of the posterior risk. Applications to low-rank matrix completion and ReLU neural network regression and classification show that the resulting bounds are analytically tractable and substantially tighter than classical complexity-based bounds. Our results highlight the potential of PAC-Bayes analysis for precise finite-sample generalization guarantees in modern overparameterized and singular models.
Chenyang Wang, Yun Yang
Department of Statistics, University of Illinois Urbana-Champaign · Department of Mathematics, University of Maryland, College Park
Overparameterized models often have continuous parameter symmetries, so different parameters define the same predictor. We show that PAC--Bayesian analysis should be performed on the quotient predictor space: pushing a prior and posterior to the quotient preserves the empirical and population Gibbs risks while removing the nonnegative KL contribution caused solely by how the two distributions differ among parameterizations of the same predictor. Quotienting alone does not determine which prior to use. We construct a canonical choice of one parameterization for each predictor and account for the geometric volume of its equivalent parameterizations. This transforms a neutral reference prior into a data-independent prior that reflects the model's implicit bias. It approximates the ideal but inadmissible posterior-matched prior, which would minimize the KL term by depending on the training data. The resulting certificate is tighter exactly when this geometry-induced prior has smaller KL divergence from the learned quotient posterior than the neutral prior. We test this prediction in Fourier regression with a Hadamard parameterization and in Query-Key attention, using ordinary SGD without an explicit regularizer. The implicit-bias prior reduces the mean quotient-space KL by 40.69% and the mean PAC--Bayes certificate by 21.40% in the Fourier-Hadamard experiment. The smaller, prior-scale-dependent improvement in Query-Key attention confirms the predicted conditional nature of the effect.
Nicola Aladrah, Fabio Anselmi
Department of Mathematics, Informatics and Geoscience, University of Trieste, Via Valerio 12/1, 34127 Trieste, Italy · 2McGovern Institute, MIT, Main Street, Cambridge, MA 02139, USA