Structural risk minimization over data-dependent hierarchies
From MaRDI portal
Publication:4701167
DOI10.1109/18.705570zbMath0935.68090OpenAlexW2106491486MaRDI QIDQ4701167
Bartlett, Peter L., Robert C. Williamson, John Shawe-Taylor, Martin Anthony
Publication date: 21 November 1999
Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)
Full work available at URL: https://semanticscholar.org/paper/1f5a3dc5867218b86ab29cbf0046f2a02ee6ded5
Related Items (51)
Complexity regularization via localized random penalties ⋮ Generalization bounds for averaged classifiers ⋮ Tikhonov, Ivanov and Morozov regularization for support vector machine learning ⋮ On data classification by iterative linear partitioning ⋮ Large width nearest prototype classification on general distance spaces ⋮ Kernels as features: on kernels, margins, and low-dimensional mappings ⋮ Recurrent Neural Networks with Small Weights Implement Definite Memory Machines ⋮ Complexity of hyperconcepts ⋮ Multi-kernel regularized classifiers ⋮ Ten More Years of Error Rate Research ⋮ Classification based on prototypes with spheres of influence ⋮ Why does deep and cheap learning work so well? ⋮ On the generalization error of fixed combinations of classifiers ⋮ Tests and classification methods in adaptive designs with applications ⋮ Robust cutpoints in the logical analysis of numerical data ⋮ Unnamed Item ⋮ Hybrid evolutionary algorithms in a SVR traffic flow forecasting model ⋮ On biased random walks, corrupted intervals, and learning under adversarial design ⋮ Estimation of convergence rate for multi-regression learning algorithm ⋮ Learning bounds via sample width for classifiers on finite metric spaces ⋮ The true sample complexity of active learning ⋮ The maximum vector-angular margin classifier and its fast training on large datasets using a core vector machine ⋮ An improved analysis of the Rademacher data-dependent bound using its self bounding property ⋮ On learning multicategory classification with sample queries. ⋮ A hybrid classifier based on boxes and nearest neighbors ⋮ Data Dependent Priors in PAC-Bayes Bounds ⋮ Derivative reproducing properties for kernel methods in learning theory ⋮ Regularization Techniques and Suboptimal Solutions to Optimization Problems in Learning from Data ⋮ A sharp concentration inequality with applications ⋮ Active Nearest-Neighbor Learning in Metric Spaces ⋮ Aspects of discrete mathematics and probability in the theory of machine learning ⋮ Approximation with polynomial kernels and SVM classifiers ⋮ The theoretical analysis of FDA and applications ⋮ PAC-Bayesian compression bounds on the prediction error of learning algorithms for classification ⋮ A local Vapnik-Chervonenkis complexity ⋮ PAC-Bayesian compression bounds on the prediction error of learning algorithms for classification ⋮ Learning big (image) data via coresets for dictionaries ⋮ Adaptive metric dimensionality reduction ⋮ Multi-category classifiers and sample width ⋮ Comment ⋮ Making Vapnik–Chervonenkis Bounds Accurate ⋮ Theory of Classification: a Survey of Some Recent Advances ⋮ A theory of learning with similarity functions ⋮ A permutation approach to validation* ⋮ Support Vector Machines for Dyadic Data ⋮ Distribution-free consistency of empirical risk minimization and support vector regression ⋮ Optimality of SVM: novel proofs and tighter bounds ⋮ Critical properties of the SAT/UNSAT transitions in the classification problem of structured data ⋮ Unnamed Item ⋮ Unnamed Item ⋮ PAC-Bayesian inequalities of some random variables sequences
This page was built for publication: Structural risk minimization over data-dependent hierarchies
