Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization

No abstract is available for this paper.

• Publication year

  2006

• Venue

  Advances in Computational Mathematics

• Publication date

  2006-07-01

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1007/s10444-004-7634-z
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Statistical Learning Theory

  2021influential reference
• The Mathematics of Learning: Dealing with Data

  2005cited by this paper
• General conditions for predictivity in learning theory

  2004cited by this paper
• Geometric Parameters in Learning Theory

  2004influential reference
• Regression and Classification with Regularization

  2003cited by this paper
• The covering number in learning theory

  2002cited by this paper
• Stability and Generalization

  2002influential reference
• Almost-everywhere Algorithmic Stability and Generalization Error

  2002influential reference
• Statistical Learning: Stability is Sufficient for Generalization and Necessary and Sufficient for Consistency of Empirical Risk Minimization

  2002cited by this paper
• Uniform Central Limit Theorems

  2001cited by this paper
• UNIFORM CENTRAL LIMIT THEOREMS (Cambridge Studies in Advanced Mathematics 63) By R. M. D UDLEY : 436pp., £55.00, ISBN 0-521-46102-2 (Cambridge University Press, 1999).

  2001cited by this paper
• On the mathematical foundations of learning

  2001influential reference
• Algorithmic Stability and Generalization Performance

  2000cited by this paper
• Regularization Networks and Support Vector Machines

  2000cited by this paper
• A General Class of Exponential Inequalities for Martingales and Ratios

  1999cited by this paper
• Algorithmic Stability and Sanity-Check Bounds for Leave-One-Out Cross-Validation

  1997cited by this paper
• Majorizing measures: the generic chaining

  1996cited by this paper
• A Probabilistic Theory of Pattern Recognition

  1996cited by this paper
• A new look at independence

  1996cited by this paper
• Scale-sensitive dimensions, uniform convergence, and learnability

  1993influential reference
• Type, infratype and the Elton-Pajor theorem

  1992cited by this paper
• Uniform and universal Glivenko-Cantelli classes

  1991influential reference
• A dimension reduction framework for understanding cortical maps

  1990cited by this paper
• Ill-posed problems in early vision

  1988influential reference
• A theory of the learnable

  1984cited by this paper
• A theory of the learnable

  1984cited by this paper
• Distribution-free performance bounds for potential function rules

  1979influential reference
• Solutions of ill-posed problems

  1977cited by this paper
• Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities

  1971cited by this paper
• ON CONVERGENCE OF STOCHASTIC PROCESSES

  1962cited by this paper
• and as an in

  year unknowncited by this paper
• Stability of

  year unknowncited by this paper

• Reconciling grokking with statistical learning theory through the lens of norm- and stability-based generalization bounds

  2026cites this paper
• Conformal Risk Control for Non-Monotonic Losses

  2026cites this paper
• Exploring the Influence of Visual Aids in Mathematical Problem Solving: An Eye-Tracking Study With Prospective Teachers

  2025cites this paper
• Informed Machine Learning: Excess risk and generalization

  2025cites this paper
• The Relative Instability of Model Comparison with Cross-validation

  2025cites this paper
• Optimizer-dependent generalization bound for quantum neural networks

  2025cites this paper
• Total stability of outcome weighted learning

  2025cites this paper
• Tight Generalization Error Bounds for Stochastic Gradient Descent in Non-convex Learning

  2025cites this paper
• From Feature‐Based Chemical Similarity to Chemical Language Models—A Paradigm Shift in Computer‐Aided Molecular Design and Property Predictions

  2025cites this paper
• Probabilistic Confusion Matrix: A Novel Method for Machine Learning Algorithm Generalized Performance Analysis

  2024cites this paper
• Error Bounds of Supervised Classification from Information-Theoretic Perspective

  2024cites this paper
• Investigating over-parameterized randomized graph networks

  2024cites this paper
• Learning Variational Inequalities from Data: Fast Generalization Rates under Strong Monotonicity

  2024cites this paper
• Stability via resampling: statistical problems beyond the real line

  2024cites this paper
• Is Cross-validation the Gold Standard to Estimate Out-of-sample Model Performance?

  2024cites this paper
• Towards algorithms and models that we can trust: A theoretical perspective

  2024cites this paper
• On the Stability and Generalization of Meta-Learning

  2024cites this paper
• GenEFT: Understanding statics and dynamics of model generalization via physics-inspired effective theory.

  2024cites this paper
• Is Cross-Validation the Gold Standard to Evaluate Model Performance?

  2024cites this paper
• Memorization in Deep Learning: A Survey

  2024cites this paper
• Evaluating Self-Supervised Learning via Risk Decomposition

  2023cites this paper
• Sharper Analysis for Minibatch Stochastic Proximal Point Methods: Stability, Smoothness, and Deviation

  2023cites this paper
• Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation

  2023cites this paper
• Probabilistic Robustness for Data Filtering

  2023cites this paper
• Bagging Provides Assumption-free Stability

  2023cites this paper
• Online-to-PAC Conversions: Generalization Bounds via Regret Analysis

  2023cites this paper
• Stability and L2-penalty in Model Averaging

  2023cites this paper
• A Path to Simpler Models Starts With Noise

  2023cites this paper
• Generalization as Dynamical Robustness-The Role of Riemannian Contraction in Supervised Learning

  2023cites this paper
• L2-Uniform Stability of Randomized Learning Algorithms: Sharper Generalization Bounds and Confidence Boosting

  2023cites this paper
• Towards a Risk-Based Continuous Auditing-Based Certification for Machine Learning

  2023cites this paper
• Toward Understanding the Generalizability of Delayed Stochastic Gradient Descent

  2023cites this paper
• Stability and Generalization of Hypergraph Collaborative Networks

  2023cites this paper
• How Spurious Features are Memorized: Precise Analysis for Random and NTK Features

  2023cites this paper
• Self-Compatibility: Evaluating Causal Discovery without Ground Truth

  2023cites this paper
• Understanding quantum machine learning also requires rethinking generalization

  2023cites this paper
• Do we really need a new theory to understand over-parameterization?

  2023cites this paper
• Generalization Error of First-Order Methods for Statistical Learning with Generic Oracles

  2023cites this paper
• Multi-relational graph convolutional networks: Generalization guarantees and experiments

  2023cites this paper
• Exponential Generalization Bounds with Near-Optimal Rates for $L_q$-Stable Algorithms

  2023cites this paper
• Enhancing interpretability and generalizability of deep learning-based emulator in three-dimensional lake hydrodynamics using Koopman operator and transfer learning: Demonstrated on the example of lake Zurich.

  2023cites this paper
• LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation

  2023cites this paper
• Black-Box Generalization

  2022cites this paper
• Sampling matters: SGD smoothing through importance sampling

  2022cites this paper
• On Stability and Generalization of Bilevel Optimization Problem

  2022cites this paper
• Resampling Sensitivity of High-Dimensional PCA

  2022cites this paper
• Stability and Risk Bounds of Iterative Hard Thresholding

  2022cites this paper
• On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond

  2022cites this paper
• Reconstructing Chromatic-Dispersion Relations and Predicting Refractive Indices Using Text Mining and Machine Learning

  2022cites this paper
• Uniform Stability for First-Order Empirical Risk Minimization

  2022cites this paper
• Boosting the Confidence of Generalization for L2-Stable Randomized Learning Algorithms

  2022cites this paper
• Generalization Error Bounds : ZoSS vs SGD Algorithm Bound

  2022cites this paper
• Enhanced multiclass support vector data description model for fault diagnosis of gears

  2022cites this paper
• Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks

  2022cites this paper
• Generalization in Supervised Learning Through Riemannian Contraction

  2022cites this paper
• L G ] 3 0 O ct 2 01 9 Risk Bounds for Reservoir Computing

  2022cites this paper
• Distribution of Classification Margins: Are All Data Equal?

  2021cites this paper
• Towards effective metamorphic testing by algorithm stability for linear classification programs

  2021cites this paper
• Robust pairwise learning with Huber loss

  2021cites this paper
• Error Estimates for Neural Network Solutions of Partial Differential Equations

  2021cites this paper
• RATT: Leveraging Unlabeled Data to Guarantee Generalization

  2021cites this paper
• Updating the paradigm of official statistics: New quality criteria for integrating new data and methods in official statistics

  2021cites this paper
• Black box tests for algorithmic stability

  2021cites this paper
• Counterfactual Memorization in Neural Language Models

  2021cites this paper
• Computational Learning Theory

  2021cites this paper
• Artificial Neural Networks for Educational Data Mining in Higher Education: A Systematic Literature Review

  2021influential citation
• Distribution-Dependent Weighted Union Bound †

  2021cites this paper
• Adaptive risk prediction system with incremental and transfer learning

  2021cites this paper
• Neural ODE Control for Classification, Approximation, and Transport

  2021cites this paper
• Right to Be Forgotten in the Age of Machine Learning

  2021cites this paper
• Cross-validation Stability of Deep Networks

  2021cites this paper
• Stable Foundations for Learning: a foundational framework for learning theory in both the classical and modern regime.

  2020influential citation
• A Closer Look at the Training Strategy for Modern Meta-Learning

  2020cites this paper
• Supervised learning as an inverse problem based on non-smooth loss function

  2020cites this paper
• Generalization Bounds for Stochastic Saddle Point Problems

  2020cites this paper
• The generalization error of graph convolutional networks may enlarge with more layers

  2020cites this paper
• Scaling-Up Distributed Processing of Data Streams for Machine Learning

  2020cites this paper
• Target-Embedding Autoencoders for Supervised Representation Learning

  2020cites this paper
• Statistical Computational Learning

  2020cites this paper
• A Deep Learning Example: the Generic Vector Projection Model, Interpolation and Generalization Analysis

  2020influential citation
• High probability convergence bounds for stochastic gradient descent assuming the Polyak-Lojasiewicz inequality

  2020cites this paper
• High probability convergence and uniform stability bounds for nonconvex stochastic gradient descent

  2020cites this paper
• A Tight Lower Bound for Uniformly Stable Algorithms

  2020cites this paper
• Generalization Bounds for High-dimensional M-estimation under Sparsity Constraint

  2020cites this paper
• Practical calibration of the temperature parameter in Gibbs posteriors

  2020cites this paper
• Stability Enhanced Privacy and Applications in Private Stochastic Gradient Descent

  2020cites this paper
• N ON -A SYMPTOTIC PAC-B AYES B OUNDS ON G ENER - ALIZATION E RROR

  2020cites this paper
• For interpolating kernel machines, the minimum norm ERM solution is the most stable

  2020influential citation
• Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses

  2020cites this paper
• Robustness by Reweighting for Kernel Estimators: An Overview

  2020cites this paper
• Randomized learning and generalization of fair and private classifiers: From PAC-Bayes to stability and differential privacy

  2020cites this paper
• An Overview of Some Issues in the Theory of Deep Networks

  2020cites this paper
• Large-time asymptotics in deep learning

  2020cites this paper
• Exit Through the Training Data: A Look into Instance-Attribution Explanations and Efficient Data Deletion in Machine Learning

  2020cites this paper
• GCN-LRP explanation: exploring latent attention of graph convolutional networks

  2020cites this paper
• DeepNNK: Explaining deep models and their generalization using polytope interpolation

  2020cites this paper
• Design-Unbiased Statistical Learning in Survey Sampling

  2020influential citation
• Stable Foundations for Learning: a framework for learning theory (in both the classical and modern regime).

  2020influential citation
• For Interpolating Kernel Machines, Minimizing the Norm of the ERM Solution Maximizes Stability

  2020influential citation
• Toward Better Generalization Bounds with Locally Elastic Stability

  2020cites this paper