Local Rademacher complexities and oracle inequalities in risk minimization

No abstract is available for this paper.

• Publication year

  2006

• Venue

  Annals of Statistics

• Publication date

  Unknown publication date

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1214/009083606000001028
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Reconstruction and Subgaussian Operators in Asymptotic Geometric Analysis

  2007cited by this paper
• Empirical minimization

  2006cited by this paper
• Optimal Model Assessment, Selection, and Combination

  2006cited by this paper
• Convexity, Classification, and Risk Bounds

  2006cited by this paper
• Square root penalty: Adaptation to the margin in classification and in edge estimation

  2005cited by this paper
• On weakly bounded empirical processes

  2005cited by this paper
• Optimal Sample-Based Estimates of the Expectation of the Empirical Minimizer

  2005cited by this paper
• The Elements of Statistical Learning: Data Mining, Inference, and Prediction

  2004cited by this paper
• Optimal aggregation of classifiers in statistical learning

  2003influential reference
• OF LEARNING

  2002cited by this paper
• Improving the sample complexity using global data

  2002cited by this paper
• Smooth Discrimination Analysis

  1999cited by this paper
• Minimum contrast estimators on sieves: exponential bounds and rates of convergence

  1998cited by this paper
• Probability inequalities for likelihood ratios and convergence rates of sieve MLEs

  1995cited by this paper
• Sharper Bounds for Gaussian and Empirical Processes

  1994cited by this paper
• Convergence Rate of Sieve Estimates

  1994cited by this paper
• Hellinger-Consistency of Certain Nonparametric Maximum Likelihood Estimators

  1993cited by this paper
• Rates of convergence for minimum contrast estimators

  1993cited by this paper
• Estimating a Regression Function

  1990cited by this paper
• Eecient Agnostic Learning of Neural Networks with Bounded Fan-in

  year unknowncited by this paper
• Fast Rates of Uniform Convergence and Oracle Inequalities for Model Selection

  year unknowncited by this paper

• Compact Vision Transformer by Reduction of Kernel Complexity

  2025cites this paper
• Overfitting has a limitation: a model-independent generalization gap bound based on R\'enyi entropy

  2025cites this paper
• Some Robustness Properties of Label Cleaning

  2025cites this paper
• System-Aware Unlearning Algorithms: Use Lesser, Forget Faster

  2025cites this paper
• Overfitting has a limitation: a model-independent generalization error bound based on Rényi entropy

  2025cites this paper
• Solving PDEs on spheres with physics-informed convolutional neural networks

  2025cites this paper
• Deep learning for Markov chains: Lyapunov functions, Poisson’s equation, and stationary distributions

  2025influential citation
• Complexity Dependent Error Rates for Physics-informed Statistical Learning via the Small-ball Method

  2025cites this paper
• A Few Observations on Sample-Conditional Coverage in Conformal Prediction

  2025cites this paper
• Universal Rates of ERM for Agnostic Learning

  2025influential citation
• Interval-Valued Time Series Classification Using DK-Distance

  2025cites this paper
• Upper Bounds on Averaged Sampling Numbers for General Model Classes

  2025cites this paper
• Simple and Sharp Generalization Bounds via Lifting

  2025cites this paper
• Vector Contrastive Learning For Pixel-Wise Pretraining In Medical Vision

  2025cites this paper
• Shallow Neural Networks Learn Low-Degree Spherical Polynomials with Learnable Channel Attention

  2025cites this paper
• Local convergence rates of the nonparametric least squares estimator with applications to transfer learning

  2024cites this paper
• Evaluating model performance under worst-case subpopulations

  2024cites this paper
• The Generalization Error of Supervised Machine Learning Algorithms

  2024cites this paper
• Asset pricing with neural networks: Significance tests

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

  2024cites this paper
• An Adversarially Robust Formulation of Linear Regression With Missing Data

  2024cites this paper
• Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regression: A Distribution-Free Analysis

  2024cites this paper
• An error analysis for deep binary classification with sigmoid loss

  2024cites this paper
• Simultaneous Confidence Intervals for Signal Detection and Ascertaining Precision of Adverse Event Rates in Clinical Trials

  2024cites this paper
• Forecasting the cost of drought events in France by Super Learning from a short time series of many slightly dependent data

  2024cites this paper
• Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking

  2024influential citation
• Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation

  2024cites this paper
• On the Efficiency of ERM in Feature Learning

  2024cites this paper
• Is Offline Decision Making Possible with Only Few Samples? Reliable Decisions in Data-Starved Bandits via Trust Region Enhancement

  2024influential citation
• Learning Low-Rank Feature for Thorax Disease Classification

  2024influential citation
• Adaptive Sample Aggregation In Transfer Learning

  2024influential citation
• Learning Variational Inequalities from Data: Fast Generalization Rates under Strong Monotonicity

  2024influential citation
• Distribution-Free Rates in Neyman-Pearson Classification

  2024cites this paper
• Exploring Local Norms in Exp-concave Statistical Learning

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

  2023influential citation
• Deep Regression for Repeated Measurements

  2023cites this paper
• The Effective Horizon Explains Deep RL Performance in Stochastic Environments

  2023influential citation
• On Excess Risk Convergence Rates of Neural Network Classifiers

  2023cites this paper
• Scalable Statistical Inference in Non-parametric Least Squares

  2023cites this paper
• Statistical Spatially Inhomogeneous Diffusion Inference

  2023cites this paper
• Nonasymptotic analysis of robust regression with modified Huber's loss

  2023cites this paper
• Sampling-based Nyström Approximation and Kernel Quadrature

  2023cites this paper
• Solving PDEs on Spheres with Physics-Informed Convolutional Neural Networks

  2023cites this paper
• of the Bernoulli Society for Mathematical Statistics and Probability Volume Twenty Nine Number Four November 2023

  2023cites this paper
• Risk-Averse Trajectory Optimization via Sample Average Approximation

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

  2023cites this paper
• Nonparametric regression using over-parameterized shallow ReLU neural networks

  2023influential citation
• Optimal Rate of Kernel Regression in Large Dimensions

  2023cites this paper
• Distribution-Free Model-Agnostic Regression Calibration via Nonparametric Methods

  2023cites this paper
• Fast Excess Risk Rates via Offset Rademacher Complexity

  2023influential citation
• Limits of Model Selection under Transfer Learning

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

  2023cites this paper
• On the Concentration of the Minimizers of Empirical Risks

  2023cites this paper
• Tight and fast generalization error bound of graph embedding in metric space

  2023influential citation
• Task Variance Regularized Multi-Task Learning

  2023cites this paper
• Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond

  2023cites this paper
• Nonparametric Estimation for High-Dimensional Space Models Based on a Deep Neural Network

  2023cites this paper
• From oracle generalization bound toward empirical inequality

  2023cites this paper
• Sharper Utility Bounds for Differentially Private Models: Smooth and Non-smooth

  2022influential citation
• An elementary analysis of ridge regression with random design

  2022cites this paper
• Locally simultaneous inference

  2022cites this paper
• Exponential Tail Local Rademacher Complexity Risk Bounds Without the Bernstein Condition

  2022cites this paper
• Policy learning "without" overlap: Pessimism and generalized empirical Bernstein's inequality

  2022cites this paper
• Concentration and robustness of discrepancy–based abc via Rademacher complexity

  2022cites this paper
• Robust supervised learning with coordinate gradient descent

  2022cites this paper
• of the Bernoulli Society for Mathematical Statistics and Probability Volume Twenty Eight Number Two May 2022

  2022cites this paper
• Optimal Regularized Online Allocation by Adaptive Re-Solving

  2022cites this paper
• On Catoni's M-Estimation

  2022cites this paper
• Randomized Sketches for Clustering: Fast and Optimal Kernel $k$-Means

  2022cites this paper
• Federated Learning on Adaptively Weighted Nodes by Bilevel Optimization

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

  2022cites this paper
• Generalization Bounds for Data-Driven Numerical Linear Algebra

  2022cites this paper
• Sample Average Approximation for Stochastic Programming with Equality Constraints

  2022influential citation
• ActiveHedge: Hedge meets Active Learning

  2022cites this paper
• A Moment-Matching Approach to Testable Learning and a New Characterization of Rademacher Complexity

  2022cites this paper
• The benefits of adversarial defense in generalization

  2022cites this paper
• Optimal robust mean and location estimation via convex programs with respect to any pseudo-norms

  2021cites this paper
• Rademacher complexity of noisy quantum circuits

  2021cites this paper
• Statistical Inference after Kernel Ridge Regression Imputation under item nonresponse

  2021cites this paper
• The Smoking Gun: Statistical Theory Improves Neural Network Estimates

  2021cites this paper
• Stability and Deviation Optimal Risk Bounds with Convergence Rate O(1/n)

  2021influential citation
• Parting Thoughts

  2021cites this paper
• Statistical inference using regularized M-estimation in the reproducing kernel Hilbert space for handling missing data

  2021influential citation
• One-step ahead sequential Super Learning from short times series of many slightly dependent data, and anticipating the cost of natural disasters

  2021cites this paper
• Sharper Generalization Bounds for Clustering

  2021cites this paper
• Towards Understanding Generalization via Decomposing Excess Risk Dynamics

  2021cites this paper
• On Empirical Risk Minimization with Dependent and Heavy-Tailed Data

  2021cites this paper
• Weighted Training for Cross-Task Learning

  2021cites this paper
• Statistical optimality conditions for compressive ensembles

  2021cites this paper
• BanditMTL: Bandit-based Multi-task Learning for Text Classification

  2021cites this paper
• Uncertainty quantification for distributed regression

  2021cites this paper
• Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning

  2021cites this paper
• Convergence rates for shallow neural networks learned by gradient descent

  2021cites this paper
• Refined Learning Bounds for Kernel and Approximate $k$-Means

  2021cites this paper
• Concentration inequalities for two-sample rank processes with application to bipartite ranking

  2021cites this paper
• Concentration bounds for the empirical angular measure with statistical learning applications

  2021cites this paper
• Constrained Classification and Policy Learning

  2021cites this paper
• Optimal and instance-dependent oracle inequalities for policy evaluation

  2021cites this paper
• Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics

  2020cites this paper
• Early stopping and polynomial smoothing in regression with reproducing kernels

  2020cites this paper