The Shape of Learning Curves: A Review
Open accessThe DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
Learning curves provide insight into the dependence of a learner's generalization performance on the training set size. This important tool can be used for model selection, to predict the effect of more training data, and to reduce the computational complexity of model training and hyperparameter tuning. This review recounts the origins of the term, provides a formal definition of the learning curve, and briefly covers basics such as its estimation. Our main contribution is a comprehensive overview of the literature regarding the shape of learning curves. We discuss empirical and theoretical evidence that supports well-behaved curves that often have the shape of a power law or an exponential. We consider the learning curves of Gaussian processes, the complex shapes they can display, and the factors influencing them. We draw specific attention to examples of learning curves that are ill-behaved, showing worse learning performance with more training data. To wrap up, we point out various open problems that warrant deeper empirical and theoretical investigation. All in all, our review underscores that learning curves are surprisingly diverse and no universal model can be identified.
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
Nearest neighbor pattern classification
Cover, T., & Hart, P. (1967) · IEEE Transactions on Information Theory · doi:10.1109/tit.1967.1053964 · Cited by 16,936
The perceptron: A probabilistic model for information storage and organization in the brain.
Rosenblatt, F. (1958) · Psychological Review · doi:10.1037/h0042519 · Cited by 12,280
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550
A Probabilistic Theory of Pattern Recognition
Devroye, L., Györfi, L., & Lugosi, G. (1996) · Stochastic Modelling and Applied Probability · doi:10.1007/978-1-4612-0711-5 · Cited by 3,274 · cited 1×
“1 in [99], gives an insightful case of dipping for likelihood estimation.”
BackgroundUnderstanding Machine Learning: From Theory to Algorithms
Shalev-Shwartz, S., & Ben-David, S. (2014) · doi:10.1017/cbo9781107298019 · Cited by 3,115
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.97 · Cited by 2,484
Estimating the error rate of a prediction rule: improvement on cross-validation
Efron, B. (1983) · Journal of the American Statistical Association · doi:10.1080/01621459.1983.10477973 · Cited by 2,300 · cited 1×
“Alternatively, the bootstrap can also be considered to come to variable sized training sets [31, 32].”
BackgroundCover, T. M. (1965) · IEEE Transactions on Electronic Computers · doi:10.1109/pgec.1965.264137 · Cited by 2,044
Reconciling modern machine-learning practice and the classical bias–variance trade-off
Belkin, M., Hsu, D., Ma, S., & Mandal, S. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1903070116 · Cited by 1,595
Small sample size effects in statistical pattern recognition: Recommendations for practitioners
Raudys, S. J., & Jain, A. K. (1991) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.75512 · Cited by 1,384
Zhai, X., Kolesnikov, A., Houlsby, N., & Beyer, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01179 · Cited by 891
Deep double descent: where bigger models and more data hurt*
Nakkiran, P., Kaplun, G., Bansal, Y., Yang, T., Barak, B., & Sutskever, I. (2021) · Journal of Statistical Mechanics: Theory and Experiment · doi:10.1088/1742-5468/ac3a74 · Cited by 565 · cited 4×
“Instead of changing the dimensionality, changing parameters of the learner, such as the smoothness of a kernel or the amount of filters in a CNN, can also be used to vary the complexity to obtain similar curves [51], [53], [54], [55], [56].”
BackgroundMethodInfluentialStatistical 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
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 · cited 5×
“Kaplan et al. [111] and Rosenfeld et al. [73] also rely on power laws for image classification and natural language processing and remarks similar to those we made about [98] apply.”
BackgroundMethodInfluentialMachine learning as an experimental science
Langley, P. (1988) · Machine Learning · doi:10.1007/bf00115008 · Cited by 187
Artifactual power curves in forgetting
Anderson, R. B., & Tweney, R. D. (1997) · Memory & Cognition · doi:10.3758/bf03211315 · Cited by 129
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
Power, A., Burda, Y., Edwards, H., Babuschkin, I., & Misra, V. (2022) · arXiv · doi:10.48550/arxiv.2201.02177 · Cited by 83
A Constructive Prediction of the Generalization Error Across Scales
Rosenfeld, J. S., Rosenfeld, A., Belinkov, Y., & Shavit, N. (2019) · arXiv · doi:10.48550/arxiv.1909.12673 · Cited by 74
Data and Parameter Scaling Laws for Neural Machine Translation
Gordon, M. A., Duh, K., & Kaplan, J. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.478 · Cited by 31 · cited 1×
“Some recent additions to this quickly expanding field are [112] and [113].”
Background
Cited by
Ghasemzadeh, H., Hillman, R. E., & Mehta, D. D. (2024) · Journal of Speech, Language, and Hearing Research · doi:10.1044/2023_jslhr-23-00273 · Cited by 72
Metadata
- Authors
- Viering, T., & Loog, M.
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2023-06-01
- Volume
- 45
- Issue
- 6
- Pages
- 7799-7819
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W3136016591
- Cited by
- 205
- References
- 19
- FWCI
- 12.12
- Type
- journal article
- Language
- en
- Open access
- green
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
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.