The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Some PAC-Bayesian theorems
Abstract
This paper gives PAC guarantees for "Bayesian" algorithms --- algorithms that optimize risk minimization expressions involving a prior probability and a likelihood for the training data. PAC-Bayesian algorithms are motivated by a desire to provide an informative prior encoding information about the expected experimental setting but still having PAC performance guarantees over all IID settings. The PACBayesian theorems given here apply to an arbitrary prior measure on an arbitrary concept space. These theorems provide an alternative to the use of VC dimension in proving PAC bounds for parameterized concepts. 1 INTRODUCTION Much of modern learning theory can be divided into two seemingly separate areas --- Bayesian inference and PAC learning. Both areas study learning algorithms which take as input training data and produce as output a concept or model which can then be tested on test data. In both areas learning algorithms are associated with correctness theorems. PAC correct...
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Minimum complexity density estimation
Barron, A. R., & Cover, T. M. (1991) · IEEE Transactions on Information Theory · doi:10.1109/18.86996 · Cited by 497
An experimental and theoretical comparison of model selection methods
Kearns, M., Mansour, Y., Ng, A. Y., & Ron, D. (1995) · Proceedings of the eighth annual conference on Computational learning theory - COLT '95 · doi:10.1145/225298.225301 · Cited by 167
A PAC analysis of a Bayesian estimator
Shawe-Taylor, J., & Williamson, R. C. (1997) · Proceedings of the tenth annual conference on Computational learning theory - COLT '97 · doi:10.1145/267460.267466 · Cited by 167
Complexity Regularization with Application to Artificial Neural Networks
Barron, A. R. (1991) · Nonparametric Functional Estimation and Related Topics · doi:10.1007/978-94-011-3222-0_42 · Cited by 160
A framework for structural risk minimisation
Shawe-Taylor, J. S., Bartlett, P. L., Williamson, R. C., & Anthony, M. (1996) · Conference on Learning Theory · doi:10.1145/238061.238070 · Cited by 79
Results on learnability and the Vapnik-Chervonenkis dimension
Linial, N., Mansour, Y., & Rivest, R. L. (1991) · Information and Computation · doi:10.1016/0890-5401(91)90058-a · Cited by 69
Concept learning using complexity regularization
Lugosi, G., & Zeger, K. (1996) · IEEE Transactions on Information Theory · doi:10.1109/18.481777 · Cited by 64
Cited by
Human-level concept learning through probabilistic program induction
Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015) · Science · doi:10.1126/science.aab3050 · Cited by 2,817
(2015) · Cited by 2,857
Philosophy and the practice of Bayesian statistics
Gelman, A., & Shalizi, C. R. (2013) · British Journal of Mathematical and Statistical Psychology · doi:10.1111/j.2044-8317.2011.02037.x · Cited by 825
Theory of Classification: a Survey of Some Recent Advances
Boucheron, S., Bousquet, O., & Lugosi, G. (2005) · ESAIM: Probability and Statistics · doi:10.1051/ps:2005018 · Cited by 436
McAllester, D. A. (1999) · Proceedings of the twelfth annual conference on Computational learning theory · doi:10.1145/307400.307435 · Cited by 354
Self-citation
Metadata
- Authors
- McAllester, D. A.
- Venue
- Proceedings of the eleventh annual conference on Computational learning theory
- Publisher
- ACM
- Published
- 1998-07-24
- Pages
- 230-234
- OpenAlex
- W2014384147
- Cited by
- 464
- References
- 7
- FWCI
- 6.35
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Some PAC-Bayesian theorems. https://app.cochat.ai/papers/10.1145/279943.279989
- The paper
- McAllester, D. A. (1998). Some PAC-Bayesian theorems. Proceedings of the eleventh annual conference on Computational learning theory. https://doi.org/10.1145/279943.279989
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.