Pith. sign in

REVIEW 13 cited by

A Note on the PAC Bayesian Theorem

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv cs/0411099 v1 pith:7DSRXRC7 submitted 2004-11-30 cs.LG cs.AI

classification cs.LGcs.AI
keywords bayesiantheoremaveragesboundcountdependenceenumeratorexponential
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We prove general exponential moment inequalities for averages of [0,1]-valued iid random variables and use them to tighten the PAC Bayesian Theorem. The logarithmic dependence on the sample count in the enumerator of the PAC Bayesian bound is halved.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Beyond Modern Asymptotics for Log-Likelihood Ratios in Logistic Regression

    math.ST 2026-08 conditional novelty 8.0 of 10

    The worst-case (1−δ) quantile of the logistic log-likelihood ratio is d log(en/d)+log(1/δ) for n≥d≥3, with d=2 at log log log n and d=1 at log(1/δ).

  2. Statistically Meaningful Geometry (SMG) Beyond the Euclidean Paradigm, with Application to Generative AI

    cs.LG 2026-07 conditional novelty 7.0 of 10

    Connection-filtered horizontal learning on an Orlicz fiber bundle bounds OOD predictive variance by the diameter of the identifiable base and eliminates catastrophic forgetting by orthogonal projection of updates.

  3. Pointwise Generalization in Deep Neural Networks

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.

  4. Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime

    cs.LG 2025-10 conditional novelty 7.0 of 10

    New PAC-Bayes bounds for the Gibbs posterior remain non-vacuous in the interpolation regime and can be approximated by Langevin Monte Carlo, but the tight experimental numbers rely on an unproved random-label calibrat...

  5. PAC-Bayesian Certificates for Quadratic Closed-Loop Control

    eess.SY 2026-06 unverdicted novelty 6.0 of 10

    PAC-Bayesian bounds are derived for quadratic closed-loop control via SLS parameterization, yielding Chernoff certificates for posteriors over responses, a mean-response deployment result, and a data-driven learning a...

  6. Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Introduces a fairness layer for deep learning models that guarantees output parity and an online primal-dual algorithm for aggregate fairness guarantees in streaming predictions with small batch sizes.

  7. Bound to Disagree: Generalization Bounds via Certifiable Surrogates

    cs.LG 2026-02 conditional novelty 6.0 of 10

    A disagreement-based certificate bounds any model's true risk by adding a concentration bound on unlabeled-data disagreement to a certified surrogate's risk.

  8. Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel

    cs.LG 2025-06 reject novelty 6.0 of 10

    A computable generalization bound for gradient flow via the loss path kernel is proposed, but the proof's key Rademacher complexity lemma is false due to an underestimated chaos term.

  9. Generalization Guarantees for Multi-View Representation Learning and Application to Regularization via Gaussian Product Mixture Prior

    stat.ML 2025-04 conditional novelty 6.0 of 10

    Multi-view representation learning generalization is bounded by the MDL of latent variables, and a Gaussian product mixture regularizer built from these bounds improves test accuracy over VIB baselines.

  10. Federated Learning with Nonvacuous Generalisation Bounds

    cs.LG 2023-10 unverdicted novelty 6.0 of 10

    Federated learning trains private local randomised predictors whose aggregation yields a global predictor with nonvacuous PAC-Bayesian generalisation bounds and near-centralized accuracy.

  11. Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    Establishes a complete non-asymptotic theory of rational commitment thresholds for BMA over BDTs with Dirichlet-Multinomial leaves and Catalan-exponential tree-size priors.

  12. Margin-Adaptive Confidence Ranking for Reliable LLM Judgement

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    Learning a margin-based confidence ranker for LLM judges improves agreement-target success in cascaded selective evaluation compared to heuristic confidence scores.

  13. PAC-Bayes with Backprop

    cs.LG 2019-08 reject novelty 5.0 of 10

    Training neural networks with PAC-Bayes objectives yields MNIST test error of 1.4% and a non-vacuous risk bound of 2.3%, much tighter than prior PAC-Bayes certificates.

Pith tools