Local Rademacher complexities
From MaRDI portal
Publication:2583411
Abstract: We propose new bounds on the error of learning algorithms in terms of a data-dependent notion of complexity. The estimates we establish give optimal rates and are based on a local and empirical version of Rademacher averages, in the sense that the Rademacher averages are computed from the data, on a subset of functions with small empirical error. We present some applications to classification and prediction with convex function classes, and with kernel classes in particular.
Recommendations
Cites work
- 10.1162/153244303321897690
- A Bennett concentration inequality and its application to suprema of empirical processes
- A distribution-free theory of nonparametric regression
- A new approach to least-squares estimation, with applications
- A sharp concentration inequality with applications
- About the constants in Talagrand's concentration inequalities for empirical processes.
- Advanced lectures on machine learning. Machine learning summer school 2002, Canberra, Australia, February 11--22, 2002. Revised lectures
- Asymptotic Statistics
- Complexity regularization via localized random penalties
- Concentration inequalities using the entropy method
- Convergence of stochastic processes
- Convexity, Classification, and Risk Bounds
- Decision theoretic generalizations of the PAC model for neural net and other learning applications
- Empirical minimization
- scientific article; zbMATH DE number 2089352 (Why is no real title available?)
- scientific article; zbMATH DE number 2089354 (Why is no real title available?)
- scientific article; zbMATH DE number 5654889 (Why is no real title available?)
- scientific article; zbMATH DE number 49190 (Why is no real title available?)
- scientific article; zbMATH DE number 1246230 (Why is no real title available?)
- scientific article; zbMATH DE number 2034517 (Why is no real title available?)
- scientific article; zbMATH DE number 1552503 (Why is no real title available?)
- scientific article; zbMATH DE number 893887 (Why is no real title available?)
- Improving the sample complexity using global data
- Model selection and error estimation
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
- Rademacher averages and phase transitions in Glivenko-Cantelli classes
- Rademacher penalties and structural risk minimization
- Sharper bounds for Gaussian and empirical processes
- Smooth discrimination analysis
- Some applications of concentration inequalities to statistics
- Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
- The importance of convexity in learning with squared loss
- Une inégalité de Bennett pour les maxima de processus empiriques. (A Bennet type inequality for maxima of empirical processes)
- Uniform Central Limit Theorems
- Weak convergence and empirical processes. With applications to statistics
Cited in
(only showing first 100 items - show all)- Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions
- Convergence rates of generalization errors for margin-based classification
- Rademacher complexity in Neyman-Pearson classification
- Scale-sensitive dimensions and skeleton estimates for classification
- Direct importance estimation for covariate shift adaptation
- Learning without concentration for general loss functions
- Fast learning rate of non-sparse multiple kernel learning and optimal regularization strategies
- Local Rademacher complexity: sharper risk bounds with and without unlabeled samples
- ``Local vs. ``global parameters -- breaking the Gaussian complexity barrier
- Calibration of -insensitive loss in support vector machines regression
- Bayesian fractional posteriors
- Robust multicategory support vector machines using difference convex algorithm
- Oracle inequalities for sparse additive quantile regression in reproducing kernel Hilbert space
- Complexity regularization via localized random penalties
- Concentration estimates for learning with unbounded sampling
- On the empirical estimation of integral probability metrics
- Optimal model selection in heteroscedastic regression using piecewise polynomial functions
- Model selection by resampling penalization
- Penalized empirical risk minimization over Besov spaces
- Transfer bounds for linear feature learning
- Optimal prediction for high-dimensional functional quantile regression in reproducing kernel Hilbert spaces
- A tight upper bound on the generalization error of feedforward neural networks
- Singularity, misspecification and the convergence rate of EM
- Surrogate losses in passive and active learning
- Fast generalization error bound of deep learning without scale invariance of activation functions
- An elementary analysis of ridge regression with random design
- Convolutional spectral kernel learning with generalization guarantees
- Suboptimality of constrained least squares and improvements via non-linear predictors
- Distribution-free robust linear regression
- Influence diagnostics in support vector machines
- Empirical variance minimization with applications in variance reduction and optimal control
- Fast rates of minimum error entropy with heavy-tailed noise
- Estimation of partially conditional average treatment effect by double kernel-covariate balancing
- Robust statistical learning with Lipschitz and convex loss functions
- Convergence rates for empirical barycenters in metric spaces: curvature, convexity and extendable geodesics
- Handling concept drift via model reuse
- Convergence of online pairwise regression learning with quadratic loss
- Nonasymptotic upper bounds for the reconstruction error of PCA
- From Gauss to Kolmogorov: localized measures of complexity for ellipses
- Nonparametric distributed learning under general designs
- ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels
- A local Vapnik-Chervonenkis complexity
- Online pairwise learning algorithms with convex loss functions
- When are epsilon-nets small?
- Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions
- Convergence rates of least squares regression estimators with heavy-tailed errors
- Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation
- Rademacher complexity for Markov chains: applications to kernel smoothing and Metropolis-Hastings
- Mean estimation and regression under heavy-tailed distributions: A survey
- Minimax fast rates for discriminant analysis with errors in variables
- Generalization bounds for non-stationary mixing processes
- Online regularized learning with pairwise loss functions
- Fast rates by transferring from auxiliary hypotheses
- Complexity control in statistical learning
- On nonparametric classification with missing covariates
- Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
- Complexity of pattern classes and the Lipschitz property
- Statistical properties of kernel principal component analysis
- Model selection by bootstrap penalization for classification
- Optimal dyadic decision trees
- A unified penalized method for sparse additive quantile models: an RKHS approach
- Statistical performance of support vector machines
- Fast learning from \(\alpha\)-mixing observations
- On the uniform convergence of empirical norms and inner products, with application to causal inference
- Combinatorial bounds for learning performance
- Approximation by neural networks and learning theory
- Empirical minimization
- Complexities of convex combinations and bounding the generalization error in classification
- Boosting with early stopping: convergence and consistency
- Compressive statistical learning with random feature moments
- On mean estimation for heteroscedastic random variables
- Nonasymptotic analysis of robust regression with modified Huber's loss
- Learning without concentration
- VC dimension, fat-shattering dimension, Rademacher averages, and their applications
- On the optimal estimation of probability measures in weak and strong topologies
- Permutational Rademacher Complexity
- Consistency analysis of an empirical minimum error entropy algorithm
- Tikhonov, Ivanov and Morozov regularization for support vector machine learning
- Distribution-dependent sample complexity of large margin learning
- Newton Sketch: A Near Linear-Time Optimization Algorithm with Linear-Quadratic Convergence
- scientific article; zbMATH DE number 2089353 (Why is no real title available?)
- scientific article; zbMATH DE number 2089354 (Why is no real title available?)
- Rademacher Chaos Complexities for Learning the Kernel Problem
- On the optimality of sample-based estimates of the expectation of the empirical minimizer
- On the importance of small coordinate projections
- Selective Rademacher penalization and reduced error pruning of decision trees
- Smooth sparse coding via marginal regression for learning sparse representations
- Improvement of multiple kernel learning using adaptively weighted regularization
- scientific article; zbMATH DE number 1804106 (Why is no real title available?)
- Local learning estimates by integral operators
- Theory of Classification: a Survey of Some Recent Advances
- Noisy discriminant analysis with boundary assumptions
- Approximation error bounds via Rademacher's complexity
- Continuity of Performance Metrics for Thin Feature Maps
- Rademacher complexity and grammar induction algorithms: what it may (not) tell us
- FAST RATES FOR ESTIMATION ERROR AND ORACLE INEQUALITIES FOR MODEL SELECTION
- Inverse statistical learning
- Transductive Rademacher complexity and its applications
- Model selection in reinforcement learning
- Robustness and generalization
This page was built for publication: Local Rademacher complexities
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2583411)
