The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Statistical performance of support vector machines
Open accessAbstract
The support vector machine (SVM) algorithm is well known to the computer learning community for its very good practical results. The goal of the present paper is to study this algorithm from a statistical perspective, using tools of concentration theory and empirical processes. Our main result builds on the observation made by other authors that the SVM can be viewed as a statistical regularization procedure. From this point of view, it can also be interpreted as a model selection principle using a penalized criterion. It is then possible to adapt general methods related to model selection in this framework to study two important points: (1) what is the minimum penalty and how does it compare to the penalty actually used in the SVM algorithm; (2) is it possible to obtain “oracle inequalities” in that setting, for the specific loss function used in the SVM algorithm? We show that the answer to the latter question is positive and provides relevant insight to the former. Our result shows that it is possible to obtain fast rates of convergence for SVMs.
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
On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
Vapnik, V. N., & Chervonenkis, A. Y. (1971) · Theory of Probability & Its Applications · doi:10.1137/1116025 · Cited by 2,448
Concentration Inequalities and Model Selection
(2007) · Lecture Notes in Mathematics · doi:10.1007/978-3-540-48503-2 · Cited by 744
Self-citation
Cited by
Estimating Individualized Treatment Rules Using Outcome Weighted Learning
Zhao, Y., Zeng, D., Rush, A. J., & Kosorok, M. R. (2012) · Journal of the American Statistical Association · doi:10.1080/01621459.2012.695674 · Cited by 739
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
Self-citationKoltchinskii, V. (2011) · Lecture Notes in Mathematics · doi:10.1007/978-3-642-22147-7 · Cited by 346
Fast learning rates for plug-in classifiers
Audibert, J.-Y., & Tsybakov, A. B. (2007) · The Annals of Statistics · doi:10.1214/009053606000001217 · Cited by 326
Classification with a Reject Option using a Hinge Loss
Bartlett, P. L., & Wegkamp, M. H. (2008) · QUT ePrints (Queensland University of Technology) · doi:10.5555/1390681.1442792 · Cited by 317
Metadata
- Authors
- Blanchard, G., Bousquet, O., & Massart, P.
- Venue
- The Annals of Statistics
- Publisher
- Institute of Mathematical Statistics
- Published
- 2008-04-01
- Volume
- 36
- Issue
- 2
- Pages
- 489-531
- ISSN
- 0090-5364 (ISSN-L)
- OpenAlex
- W1983563203
- Cited by
- 167
- References
- 2
- FWCI
- 8.69
- Type
- journal article
- Language
- en
- Open access
- bronze
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: Statistical performance of support vector machines. https://app.cochat.ai/papers/10.1214/009053607000000839
- The paper
- Blanchard, G., Bousquet, O., & Massart, P. (2008). Statistical performance of support vector machines. The Annals of Statistics. https://doi.org/10.1214/009053607000000839
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.