The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Model complexity control for regression using VC generalization bounds
Abstract
It is well known that for a given sample size there exists a model of optimal complexity corresponding to the smallest prediction (generalization) error. Hence, any method for learning from finite samples needs to have some provisions for complexity control. Existing implementations of complexity control include penalization (or regularization), weight decay (in neural networks), and various greedy procedures (aka constructive, growing, or pruning methods). There are numerous proposals for determining optimal model complexity (aka model selection) based on various (asymptotic) analytic estimates of the prediction risk and on resampling approaches. Nonasymptotic bounds on the prediction risk based on Vapnik-Chervonenkis (VC)-theory have been proposed by Vapnik. This paper describes application of VC-bounds to regression problems with the usual squared loss. An empirical study is performed for settings where the VC-bounds can be rigorously applied, i.e., linear models and penalized linear models where the VC-dimension can be accurately estimated, and the empirical risk can be reliably minimized. Empirical comparisons between model selection using VC-bounds and classical methods are performed for various noise levels, sample size, target functions and types of approximating functions. Our results demonstrate the advantages of VC-based complexity control with finite samples.
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
Neural Networks for Pattern Recognition
Bishop, C. M. (1995) · doi:10.1093/oso/9780198538493.001.0001 · Cited by 12,287
Craven, P., & Wahba, G. (1978) · Numerische Mathematik · doi:10.1007/bf01404567 · Cited by 3,388
Measuring 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 2×
“This would require 1) accurate estimation of the VC-dimension in the spirit of [ 20 ] and 2) specification of the neural network settings where the global minimum of the empirical risk can be reliably found.”
Self-citation
Cited by
Practical selection of SVM parameters and noise estimation for SVM regression
Cherkassky, V., & Ma, Y. (2004) · Neural Networks · doi:10.1016/s0893-6080(03)00169-2 · Cited by 2,030
Self-citationModel complexity of deep learning: a survey
Hu, X., Chu, L., Pei, J., Liu, W., & Bian, J. (2021) · Knowledge and Information Systems · doi:10.1007/s10115-021-01605-0 · Cited by 402
Durbha, S. S., King, R. L., & Younan, N. H. (2007) · Remote Sensing of Environment · doi:10.1016/j.rse.2006.09.031 · Cited by 273
Support Vector Echo-State Machine for Chaotic Time-Series Prediction
Shi, Z., & Han, M. (2007) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2006.885113 · Cited by 258
An investigation of model selection criteria for neural network time series forecasting
Qi, M., & Zhang, G. P. (2001) · European Journal of Operational Research · doi:10.1016/s0377-2217(00)00171-5 · Cited by 256
Metadata
- Authors
- Cherkassky, V., Shao, X., Mulier, F. M., & Vapnik, V. N.
- Venue
- IEEE Transactions on Neural Networks
- Published
- 1999
- Volume
- 10
- Issue
- 5
- Pages
- 1075-1089
- ISSN
- 1045-9227 (ISSN-L)
- OpenAlex
- W2169502938
- Cited by
- 195
- References
- 3
- FWCI
- 9.77
- Type
- journal article
- 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: Model complexity control for regression using VC generalization bounds. https://app.cochat.ai/papers/10.1109/72.788648
- The paper
- Cherkassky, V., Shao, X., Mulier, F. M., & Vapnik, V. N. (1999). Model complexity control for regression using VC generalization bounds. IEEE Transactions on Neural Networks. https://doi.org/10.1109/72.788648
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.