scientific article; zbMATH DE number 17222
approximation errorartificial neural networkscomplexity of modelscomplexity regularization criteriaconsistencyindex of resolvabilityminimum description-length criteriamodel selectionnear asymptotic optimalityparameter estimation errorpolynomial regressionrates of convergencerisk boundsstatistical estimation of functions
[For the entire collection see Zbl 0722.00032.] In the context of statistical estimation of functions, a list of parametric models is provided from which one is to be automatically selected from the data. These lists of parametric models have the property that for essentially any target function there exists a convergent sequence of approximating functions of the list. In the absence of knowledge of the true function, the problem is to estimate an appropriate size model that provides a good tradeoff between the approximation error, which is best for larger models, and the parameter estimation error, which is best for smaller models. An index of resolvability is presented that defines the best tradeoff between approximation error and the complexity of models. General complexity regularization criteria are defined and bounds on the statistical risk of the estimated functions are established. These bounds establish consistency, yield rates of convergence, and demonstrate the near asymptotic optimality of the model selection criterion in both parametric and nonparametric cases. Applications are given to polynomial regression and artificial neural networks.
- Practical complexity control in multilayer perceptrons
- Bounds on the complexity of neural‐network models and comparison with linear methods
- Complexity of learning in artificial neural networks
- Complexity and neural networks
- Neural networks and complexity theory
- Complexity matching in neural networks
- scientific article; zbMATH DE number 67614
- scientific article; zbMATH DE number 4155875
- Estimates of Data Complexity in Neural-Network Learning
- Approximation by Fully Complex Multilayer Perceptrons
- Gaussian model selection with an unknown variance
- Risk bounds for model selection via penalization
- Approximation and estimation bounds for artificial neural networks
- Neural networks and logistic regression: Part I
- Model selection in nonparametric regression
- Nonlinear orthogonal series estimates for random design regression
- Ridgelets: estimating with ridge functions
- Information-theoretic determination of minimax rates of convergence
- Smooth discrimination analysis
- Interpreting neural-network results: a simulation study.
- On estimation of surrogate models for multivariate computer experiments
- Functional aggregation for nonparametric regression.
- Adaptive estimation in autoregression or \(\beta\)-mixing regression via model selection
- How well can a regression function be estimated if the distribution of the (random) design is concentrated on a finite set?
- Optimal aggregation of classifiers in statistical learning.
- Synchronous Boltzmann machines can be universal approximators
- Model selection based on minimum description length
- On the rate of convergence of fully connected deep neural network regression estimates
- Analysis of the rate of convergence of fully connected deep neural network regression estimates with smooth activation function
- A multi-loss super regression learner (MSRL) with application to survival prediction using proteomics
- On deep learning as a remedy for the curse of dimensionality in nonparametric regression
- Nonparametric estimation of low rank matrix valued function
- Data-adaptive estimation of the treatment-specific mean
- Model selection by bootstrap penalization for classification
- Suboptimal behavior of Bayes and MDL in classification under misspecification
- Approximation and learning by greedy algorithms
- Nonasymptotic bounds on the \(L_{2}\) error of neural network regression estimates
- On the mathematical foundations of learning
- On the Problem in Model Selection of Neural Network Regression in Overrealizable Scenario
- Theory of Classification: a Survey of Some Recent Advances
- Hybrid machine learning model for continuous microarray time series
- Model selection in reinforcement learning
- Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ
- scientific article; zbMATH DE number 952763 (Why is no real title available?)
- scientific article; zbMATH DE number 1911043 (Why is no real title available?)
- scientific article; zbMATH DE number 778113 (Why is no real title available?)
- A new method for estimation and model selection: \(\rho\)-estimation
- Deep ReLU networks and high-order finite element methods
- scientific article; zbMATH DE number 7306865 (Why is no real title available?)
- Analysis of the rate of convergence of least squares neural network regression estimates in case of measurement errors
- Density estimation by the penalized combinatorial method
- Deep ReLU neural network approximation in Bochner spaces and applications to parametric PDEs
- Collocation approximation by deep neural ReLU networks for parametric and stochastic PDEs with lognormal inputs
- Multiclass classification with potential function rules: margin distribution and generalization
- Time-penalised trees (\texttt{TpT}): introducing a new tree-based data mining algorithm for time-varying covariates
- Quasicycles revisited: apparent sensitivity to initial conditions
- Self-regulated complexity in neural networks
- About the non-asymptotic behaviour of Bayes estimators
- Discriminatively regularized least-squares classification
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3973919)
