Rigorous learning curve bounds from statistical mechanics
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
In this paper we introduce and investigate a mathematically rigorous theory of learning curves that is based on ideas from statistical mechanics. The advantage of our theory over the well-established Vapnik-Chervonenkis theory is that our bounds can be considerably tighter in many cases, and are also more reflective of the true behavior (functional form) of learning curves. This behavior can often exhibit dramatic properties such as phase transitions, as well as power law asymptotics not explained by the VC theory. The disadvantages of our theory are that its application requires knowledge of the input distribution, and it is limited so far to finite cardinality function classes. We illustrate our results with many concrete examples of learning curve bounds derived from our theory.
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
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
Statistical mechanics of learning from examples
Seung, H. S., Sompolinsky, H., & Tishby, N. (1992) · Physical Review A · doi:10.1103/physreva.45.6056 · Cited by 532
Self-citationMeasuring the VC-Dimension of a Learning Machine
Vapnik, V., Levin, E., & Cun, Y. L. (1994) · Neural Computation · doi:10.1162/neco.1994.6.5.851 · Cited by 388
Cited by
Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms
Dietterich, T. G. (1998) · Neural Computation · doi:10.1162/089976698300017197 · Cited by 3,840
Predictability, Complexity, and Learning
Bialek, W., Nemenman, I., & Tishby, N. (2001) · Neural Computation · doi:10.1162/089976601753195969 · Cited by 504
Self-citationA guide to the literature on learning probabilistic networks from data
Buntine, W. (1996) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/69.494161 · Cited by 468
Deep Learning Scaling is Predictable, Empirically
Hestness, J., Narang, S., Ardalani, N., Diamos, G., Jun, H., Kianinejad, H., Patwary, M. M. A., Yang, Y., & Zhou, Y. (2017) · arXiv · doi:10.48550/arxiv.1712.00409 · Cited by 427
Algorithmic Stability and Sanity-Check Bounds for Leave-One-Out Cross-Validation
Kearns, M., & Ron, D. (1999) · Neural Computation · doi:10.1162/089976699300016304 · Cited by 407
Self-citation
Metadata
- Authors
- Haussler, D., Seung, H. S., Kearns, M., & Tishby, N.
- Venue
- Proceedings of the seventh annual conference on Computational learning theory - COLT '94
- Publisher
- ACM Press
- Published
- 1994
- Pages
- 76-87
- OpenAlex
- W2038390905
- Cited by
- 96
- References
- 3
- FWCI
- 11.66
- Type
- conference paper
- 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: Rigorous learning curve bounds from statistical mechanics. https://app.cochat.ai/papers/10.1145/180139.181018
- The paper
- Haussler, D., Seung, H. S., Kearns, M., & Tishby, N. (1994). Rigorous learning curve bounds from statistical mechanics. Proceedings of the seventh annual conference on Computational learning theory - COLT '94. https://doi.org/10.1145/180139.181018
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.