10.1162/153244302760200704

DOI10.1162/153244302760200704zbMATH Open1007.68083OpenAlexW2139338362MaRDI QIDQ4779564FDOQ4779564

Authors: Olivier Bousquet, André Elisseeff 

Publication date: 27 November 2002

Published in: CrossRef Listing of Deleted DOIs (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/153244302760200704

Recommendations

• STABILITY RESULTS IN LEARNING THEORY
• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
• scientific article
• Generalization bounds of regularization algorithms derived simultaneously through hypothesis space complexity, algorithmic stability and data quality
• A survey on learning theory. I: Stability and generalization

zbMATH Keywords

learning algorithms

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32) Nonnumerical algorithms (68W05)

Cited In (only showing first 100 items - show all)

• A tight upper bound on the generalization error of feedforward neural networks
• Measuring the Stability of Results From Supervised Statistical Learning
• Indefinite kernel network with \(l^q\)-norm regularization
• Graph-dependent implicit regularisation for distributed stochastic subgradient descent
• Title not available (Why is that?)
• The role of mutual information in variational classifiers
• Data-Driven Optimization: A Reproducing Kernel Hilbert Space Approach
• Title not available (Why is that?)
• Kernel selection with spectral perturbation stability of kernel matrix
• Concept drift detection and adaptation with hierarchical hypothesis testing
• A Bernstein-type inequality for functions of bounded interaction
• Bounding the difference between RankRC and RankSVM and application to multi-level rare class kernel ranking
• Stability and generalization of graph convolutional networks in eigen-domains
• Kernelized elastic net regularization: generalization bounds, and sparse recovery
• Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution
• State-based confidence bounds for data-driven stochastic reachability using Hilbert space embeddings
• Generalization bounds for regularized portfolio selection with market side information
• Hausdorff dimension, heavy tails, and generalization in neural networks*
• Perturbation to enhance support vector machines for classification.
• Understanding generalization error of SGD in nonconvex optimization
• From undecidability of non-triviality and finiteness to undecidability of learnability
• Analysis of classifiers' robustness to adversarial perturbations
• Post-selection inference via algorithmic stability
• Title not available (Why is that?)
• Title not available (Why is that?)
• Large margin vs. large volume in transductive learning
• A selective overview of deep learning
• Title not available (Why is that?)
• Generalization Error in Deep Learning
• Learning rates of gradient descent algorithm for classification
• Stability and optimization error of stochastic gradient descent for pairwise learning
• OCReP: an optimally conditioned regularization for pseudoinversion based neural training
• On group-wise \(\ell_p\) regularization: theory and efficient algorithms
• Multiple spectral kernel learning and a Gaussian complexity computation
• Structured sparsity and generalization
• Benefit of Interpolation in Nearest Neighbor Algorithms
• Entropy-SGD: biasing gradient descent into wide valleys
• Design-unbiased statistical learning in survey sampling
• Stability and generalization of learning algorithm: a new framework of stability
• Interpretable machine learning: fundamental principles and 10 grand challenges
• On the complexity analysis of the primal solutions for the accelerated randomized dual coordinate ascent
• Approximation stability and boosting
• Stable Transductive Learning
• Distribution-free consistency of empirical risk minimization and support vector regression
• Multi-relational graph convolutional networks: generalization guarantees and experiments
• Good edit similarity learning by loss minimization
• Diametrical risk minimization: theory and computations
• Deep learning: a statistical viewpoint
• Communication-efficient distributed multi-task learning with matrix sparsity regularization
• Average stability is invariant to data preconditioning. Implications to exp-concave empirical risk minimization
• On reject and refine options in multicategory classification
• Title not available (Why is that?)
• Title not available (Why is that?)
• The big data newsvendor: practical insights from machine learning
• Robust pairwise learning with Huber loss
• 10.1162/153244303765208368
• Wasserstein-based fairness interpretability framework for machine learning models
• Classifier learning with a new locality regularization method
• Domain adaptation and sample bias correction theory and algorithm for regression
• Discussion of big Bayes stories and BayesBag
• On the Generalization Ability of On-Line Learning Algorithms
• Generalization bounds for metric and similarity learning
• Spectral Algorithms for Supervised Learning
• SIRUS: stable and interpretable RUle set for classification
• Robustness of general dichotomies
• Leave-One-Out Bounds for Kernel Methods
• Stability of unstable learning algorithms
• Least-square regularized regression with non-iid sampling
• Robustness and generalization
• Transfer bounds for linear feature learning
• Efficiency of classification methods based on empirical risk minimization
• Tikhonov, Ivanov and Morozov regularization for support vector machine learning
• Soft margin support vector classification as buffered probability minimization
• Boosting and instability for regression trees
• Approximations and solution estimates in optimization
• Analysis of support vector machines regression
• Oracle inequalities for cross-validation type procedures
• STABILITY RESULTS IN LEARNING THEORY
• Algorithmic stability and meta-learning
• Approximation with polynomial kernels and SVM classifiers
• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
• Stability analysis of learning algorithms for ontology similarity computation
• On learnability, complexity and stability
• The consistency of multicategory support vector machines
• Regularization techniques and suboptimal solutions to optimization problems in learning from data
• Leave-one-out cross-validation is risk consistent for Lasso
• Error bounds for \(l^p\)-norm multiple kernel learning with least square loss
• Training regression ensembles by sequential target correction and resampling
• Primal and dual model representations in kernel-based learning
• Multi-kernel regularized classifiers
• Generalization bounds of regularization algorithms derived simultaneously through hypothesis space complexity, algorithmic stability and data quality
• Support vector machines with applications
• Coefficient regularized regression with non-iid sampling
• Generalization bounds for averaged classifiers
• Generalization bounds for learning with linear, polygonal, quadratic and conic side knowledge
• Maximization of AUC and buffered AUC in binary classification
• Stability of randomized learning algorithms
• From inexact optimization to learning via gradient concentration
• The optimal solution of multi-kernel regularization learning
• Robustness of reweighted least squares kernel based regression

This page was built for publication: 10.1162/153244302760200704

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4779564)