Structural risk minimization over data-dependent hierarchies
From MaRDI portal
Publication:4701167
DOI10.1109/18.705570zbMATH Open0935.68090OpenAlexW2106491486MaRDI QIDQ4701167FDOQ4701167
Authors: John Shawe-Taylor, Peter L. Bartlett, Robert C. Williamson, 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
Recommendations
- StructED: risk minimization in structured prediction
- A stochastic gradient descent algorithm for structural risk minimisation
- Empirical risk minimizing for dynamical data structures
- Rademacher penalties and structural risk minimization
- The structural risk minimization principle of rough-stochastic samples
- Learning Theory
- Set structured global empirical risk minimizers are rate optimal in general dimensions
- Minimax problems under hierarchical structures
- Regression with stagewise minimization on risk function
Cited In (56)
- Critical properties of the SAT/UNSAT transitions in the classification problem of structured data
- On the generalization error of fixed combinations of classifiers
- PAC-Bayesian inequalities of some random variables sequences
- Making Vapnik-Chervonenkis bounds accurate
- Robust cutpoints in the logical analysis of numerical data
- Optimality of SVM: novel proofs and tighter bounds
- Recurrent Neural Networks with Small Weights Implement Definite Memory Machines
- Kernels as features: on kernels, margins, and low-dimensional mappings
- Adaptive metric dimensionality reduction
- Tikhonov, Ivanov and Morozov regularization for support vector machine learning
- Soft computing on small data sets
- Derivative reproducing properties for kernel methods in learning theory
- An improved analysis of the Rademacher data-dependent bound using its self bounding property
- On data classification by iterative linear partitioning
- On learning multicategory classification with sample queries.
- A permutation approach to validation*
- Complexity of hyperconcepts
- Approximation with polynomial kernels and SVM classifiers
- A local Vapnik-Chervonenkis complexity
- PAC-Bayesian compression bounds on the prediction error of learning algorithms for classification
- Estimation of convergence rate for multi-regression learning algorithm
- Regularization techniques and suboptimal solutions to optimization problems in learning from data
- Large width nearest prototype classification on general distance spaces
- Hybrid evolutionary algorithms in a SVR traffic flow forecasting model
- Multi-kernel regularized classifiers
- Multi-category classifiers and sample width
- A theory of learning with similarity functions
- Complexity regularization via localized random penalties
- Generalization bounds for averaged classifiers
- The maximum vector-angular margin classifier and its fast training on large datasets using a core vector machine
- Empirical risk minimizing for dynamical data structures
- Why does deep and cheap learning work so well?
- The theoretical analysis of FDA and applications
- Title not available (Why is that?)
- PAC-Bayesian compression bounds on the prediction error of learning algorithms for classification
- Active nearest-neighbor learning in metric spaces
- Classification based on prototypes with spheres of influence
- A hybrid classifier based on boxes and nearest neighbors
- Support Vector Machines for Dyadic Data
- Data dependent priors in PAC-Bayes bounds
- Learning big (image) data via coresets for dictionaries
- An easy-to-hard learning paradigm for multiple classes and multiple labels
- Ten More Years of Error Rate Research
- Distribution-free consistency of empirical risk minimization and support vector regression
- The true sample complexity of active learning
- Structured large margin machines: sensitive to data distributions
- Comment
- Tests and classification methods in adaptive designs with applications
- Learning bounds via sample width for classifiers on finite metric spaces
- A sharp concentration inequality with applications
- On biased random walks, corrupted intervals, and learning under adversarial design
- Aspects of discrete mathematics and probability in the theory of machine learning
- 10.1162/153244303765208368
- Title not available (Why is that?)
- Theory of Classification: a Survey of Some Recent Advances
- A stochastic gradient descent algorithm for structural risk minimisation
This page was built for publication: Structural risk minimization over data-dependent hierarchies
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4701167)
