Pith. sign in

REVIEW 5 cited by

A Primer on PAC-Bayesian Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1901.05353 v3 pith:YYBRQPWV submitted 2019-01-16 stat.ML cs.LG

Benjamin Guedj This is my paper · ORCID
classification stat.MLcs.LG
keywords learningaimsalgorithmicalgorithmsbayesiandevelopmentsflexibilityframework
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generalised Bayesian learning algorithms are increasingly popular in machine learning, due to their PAC generalisation properties and flexibility. The present paper aims at providing a self-contained survey on the resulting PAC-Bayes framework and some of its main theoretical and algorithmic developments.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Selective Safety Steering via Value-Filtered Decoding

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Value-filtered decoding steers LLM outputs for safety at decoding time using a value criterion with an explicit bound on false interventions controlled by one threshold hyperparameter.

  2. Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities

    cs.IT 2026-02 conditional novelty 7.0 of 10

    A unified DPI-based framework yields novel change-of-measure inequalities that produce tighter high-probability generalization bounds.

  3. PAC-Bayesian Reinforcement Learning Trains Generalizable Policies

    cs.LG 2025-10 conditional novelty 6.0 of 10

    A mixing-time-aware PAC-Bayes bound is turned into PB-SAC, an algorithm that computes tightening certified performance lower bounds during SAC training on MuJoCo tasks.

  4. A Generalized-Bayes Perspective on Counterfactual Explanations: Posterior-Based Decision-Making and Evaluation

    cs.AI 2026-07 conditional novelty 5.0 of 10

    Counterfactual explanation by distance minimization is re-derived as MAP inference in a generalized Bayes posterior, and additional posterior-based decision rules are proposed and evaluated.

  5. Position: There Is No Free Bayesian Uncertainty Quantification

    stat.ML 2025-06 conditional novelty 4.0 of 10

    Bayesian updating is reframed as an optimization problem without inherent uncertainty quantification, and a PAC-style calibration step is proposed to give predictive intervals frequentist coverage.

Pith tools