The DOI matches its Crossref record.
On the exponential value of labeled samples
Open accessAbstract
Consider the problem of classifying a sample X0 into one of two classes, using a training set Q. Let Q be composed of l labeled samples {(X1, θ1), …, (Xl, θl)} and u unlabeled samples {X′1, …, X′u}, where the labels θi are i.i.d. Bernoulli(η) random variables over the set {1, 2}, the observations {Xi}i=1l are distributed according to fθi(·) and the unlabeled observations {X′j}j=1u are independently distributed according to the mixture density fX′(·) = ηf1(·) + (1−η)f2(·). We assume that f1(·),f2(·) and η are all unknown. Let f1(·) and f2(·) belong to a known family F, and assume that the mixtures of elements of F are identifiable. Even when the number of unlabeled samples is infinite and the decision regions can therefore be identified, one still needs labeled samples to label the decision regions with the correct classification. Letting R(l, u) denote the optimal probability of error for l labeled and u unlabeled samples, and assuming that the pairwise mixtures of F are identifiable, we obtain the obvious statements R(0, u) = R(0, ∞) = 12, R(1, 0) ⪕ 2ηη, R(∞, u) = R∗, and then prove R(1, ∞) = 2R∗(1−R∗), where R∗ is the Bayes probability of error, and R(l, ∞) = R∗ + exp{ −αl + o(l)}, where the exponent α is given by −log(2√ηη∫ √f1(x)f2(x) dx). Thus the first labeled sample reduces the risk from 12 to 2R∗(1−R∗) and subsequent labeled samples in the training set reduce the probability of error exponentially fast to the Bayes risk.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Cited by
(2006) · The MIT Press eBooks · doi:10.7551/mitpress/9780262033589.001.0001 · Cited by 4,280
Text classification from labeled and unlabeled documents using EM
Nigam, K., Mccallum, A. K., Thrun, S., & Mitchell, T. (2000) · Machine Learning · doi:10.1023/a:1007692713085 · Cited by 2,736
A brief introduction to weakly supervised learning
Zhou, Z.-H. (2018) · National Science Review · doi:10.1093/nsr/nwx106 · Cited by 1,899
Introduction to Semi-Supervised Learning
Zhu, X., & Goldberg, A. B. (2009) · Synthesis Lectures on Artificial Intelligence and Machine Learning · doi:10.1007/978-3-031-01548-9 · Cited by 1,766
Introduction to Semi-Supervised Learning
Zhu, X., & Goldberg, A. B. (2009) · Synthesis lectures on artificial intelligence and machine learning · doi:10.2200/s00196ed1v01y200906aim006 · Cited by 1,022
Metadata
- Authors
- Castelli, V., & Cover, T. M.
- Venue
- Pattern Recognition Letters
- Publisher
- Elsevier BV
- Published
- 1995-01
- Volume
- 16
- Issue
- 1
- Pages
- 105-111
- ISSN
- 0167-8655 (ISSN-L)
- OpenAlex
- W2083515729
- Cited by
- 200
- References
- 0
- FWCI
- 4.79
- Type
- journal article
- Language
- en
- Open access
- hybrid
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: On the exponential value of labeled samples. https://app.cochat.ai/papers/10.1016/0167-8655(94)00074-d
- The paper
- Castelli, V., & Cover, T. M. (1995). On the exponential value of labeled samples. Pattern Recognition Letters. https://doi.org/10.1016/0167-8655(94)00074-d
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.