Convexity, Classification, and Risk Bounds
From MaRDI portal
Publication:5754926
DOI10.1198/016214505000000907zbMath1118.62330OpenAlexW1982032418MaRDI QIDQ5754926
Jon D. McAuliffe, Michael I. Jordan, Bartlett, Peter L.
Publication date: 20 August 2007
Published in: Journal of the American Statistical Association (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1198/016214505000000907
Related Items
Angle-based cost-sensitive multicategory classification, Tikhonov, Ivanov and Morozov regularization for support vector machine learning, Estimating individualized treatment rules for treatments with hierarchical structure, Learning from binary labels with instance-dependent noise, Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder), Convergence rates of deep ReLU networks for multiclass classification, Aggregation via empirical risk minimization, The new interpretation of support vector machines on statistical learning theory, Classification with asymmetric label noise: consistency and maximal denoising, Semi-supervised AUC optimization based on positive-unlabeled learning, Tutorial series on brain-inspired computing. VI: Geometrical structure of boosting algorithm, Supervised classification and mathematical optimization, Learning rates of kernel-based robust classification, Fast learning rate of non-sparse multiple kernel learning and optimal regularization strategies, On regularization algorithms in learning theory, Multi-kernel regularized classifiers, Universally consistent vertex classification for latent positions graphs, Convergence rates for empirical barycenters in metric spaces: curvature, convexity and extendable geodesics, Principled analytic classifier for positive-unlabeled learning via weighted integral probability metric, A Fisher consistent multiclass loss function with variable margin on positive examples, \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities, Rejoinder of ``Dynamic treatment regimes: technical challenges and applications, Learning rates for the kernel regularized regression with a differentiable strongly convex loss, Quantitative convergence analysis of kernel based large-margin unified machines, Learning noisy linear classifiers via adaptive and selective sampling, The C-loss function for pattern classification, Linear classifiers are nearly optimal when hidden variables have diverse effects, Statistical analysis of kernel-based least-squares density-ratio estimation, Boosting \(k\)-NN for categorization of natural scenes, Projected estimators for robust semi-supervised classification, Multiway spectral clustering: a margin-based perspective, Oracle properties of SCAD-penalized support vector machine, Estimating conditional quantiles with the help of the pinball loss, Calibrated asymmetric surrogate losses, Oracle inequalities for cross-validation type procedures, Upper bounds and aggregation in bipartite ranking, Further results on the margin explanation of boosting: new algorithm and experiments, Penalized empirical risk minimization over Besov spaces, Self-concordant analysis for logistic regression, Mirror averaging with sparsity priors, Boosting algorithms: regularization, prediction and model fitting, Margin-adaptive model selection in statistical learning, Fast learning of relational kernels, Learning with mitigating random consistency from the accuracy measure, Generalization ability of fractional polynomial models, Classification with label noise: a Markov chain sampling framework, Classification with non-i.i.d. sampling, Finite-sample analysis of \(M\)-estimators using self-concordance, Query-dependent ranking and its asymptotic properties, Learning rate of support vector machine for ranking, Kernel methods in machine learning, Does modeling lead to more accurate classification? A study of relative efficiency in linear classification, Discriminative training of conditional random fields with probably submodular constraints, Calibration of \(\epsilon\)-insensitive loss in support vector machines regression, Optimal exponential bounds on the accuracy of classification, Cost-sensitive feature selection for support vector machines, Comment on ``Hypothesis testing by convex optimization, The risk of trivial solutions in bipartite top ranking, Bounding the difference between RankRC and RankSVM and application to multi-level rare class kernel ranking, Cox process functional learning, Unregularized online learning algorithms with general loss functions, Support vector machines based on convex risk functions and general norms, Multiclass classification, information, divergence and surrogate risk, Robust multicategory support vector machines using difference convex algorithm, Parzen windows for multi-class classification, Learning from dependent observations, Calibration and regret bounds for order-preserving surrogate losses in learning to rank, Convergence rates of learning algorithms by random projection, Logistic classification with varying gaussians, Stochastic margin-based structure learning of Bayesian network classifiers, Learning rates for multi-kernel linear programming classifiers, On qualitative robustness of support vector machines, Multicategory classification via forward-backward support vector machine, Regularized margin-based conditional log-likelihood loss for prototype learning, Node harvest, Surrogate losses in passive and active learning, Classification with Gaussians and convex loss. II: Improving error bounds by noise conditions, Performance guarantees for individualized treatment rules, Statistical inference of minimum BD estimators and classifiers for varying-dimensional models, Approximation of frame based missing data recovery, A note on margin-based loss functions in classification, Deformation of log-likelihood loss function for multiclass boosting, Fast rates for support vector machines using Gaussian kernels, Fast learning rates for plug-in classifiers, Robustness of learning algorithms using hinge loss with outlier indicators, Sentiment analysis with covariate-assisted word embeddings, The structured elastic net for quantile regression and support vector classification, Soft-max boosting, Robust learning from bites for data mining, SVM-boosting based on Markov resampling: theory and algorithm, Consistency of support vector machines for forecasting the evolution of an unknown ergodic dynamical system from observations with unknown noise, On surrogate loss functions and \(f\)-divergences, Convergence rates of generalization errors for margin-based classification, Regularized ranking with convex losses and \(\ell^1\)-penalty, Sample average approximation with sparsity-inducing penalty for high-dimensional stochastic programming, Gradient learning in a classification setting by gradient descent, Nonregular and minimax estimation of individualized thresholds in high dimension with binary responses, Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling, A no-free-lunch theorem for multitask learning, Regularization of case-specific parameters for robustness and efficiency, Kernel machines with missing covariates, Set-Valued Support Vector Machine with Bounded Error Rates, Improving reinforcement learning algorithms: Towards optimal learning rate policies, Sampling and empirical risk minimization, Angle-Based Hierarchical Classification Using Exact Label Embedding, Learning theory of minimum error entropy under weak moment conditions, Deep learning: a statistical viewpoint, A Statistical Learning Approach to Modal Regression, Fully online classification by regularization, High-Dimensional Learning Under Approximate Sparsity with Applications to Nonsmooth Estimation and Regularized Neural Networks, Statistical properties of kernel principal component analysis, Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting, and Regularization, Unnamed Item, Classifiers of support vector machine type with \(\ell_1\) complexity regularization, Surrogate regret bounds for generalized classification performance metrics, Unnamed Item, ℓ1-Norm support vector machine for ranking with exponentially strongly mixing sequence, A Unified Classification Model Based on Robust Optimization, The fundamental role of density functions in the binary classification problem, Scalable Collaborative Ranking for Personalized Prediction, Receiver operating characteristic curves and confidence bands for support vector machines, A random block-coordinate Douglas-Rachford splitting method with low computational complexity for binary logistic regression, Simplex-based Multinomial Logistic Regression with Diverging Numbers of Categories and Covariates, Fully corrective gradient boosting with squared hinge: fast learning rates and early stopping, Power diagram detection with applications to information elicitation, Practicable robust stochastic optimization under divergence measures with an application to equitable humanitarian response planning, Fast convergence rates of deep neural networks for classification, Robust Boosting Algorithm Against Mislabeling in Multiclass Problems, Positive-unlabeled classification under class-prior shift: a prior-invariant approach based on density ratio estimation, Error analysis of classification learning algorithms based on LUMs loss, Unnamed Item, Unnamed Item, Unnamed Item, Unnamed Item, User-friendly Introduction to PAC-Bayes Bounds, An ODE-based neural network with Bayesian optimization, Robust logistic regression with shift parameter estimation, Statistical performance of support vector machines, Ranking and empirical minimization of \(U\)-statistics, Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning, Spectral Algorithms for Supervised Learning, Regularized sample average approximation for high-dimensional stochastic optimization under low-rankness, Data-adaptive discriminative feature localization with statistically guaranteed interpretation, A Reproducing Kernel Hilbert Space Framework for Functional Classification, Transfer Learning of Individualized Treatment Rules from Experimental to Real-World Data, Consistency and convergence rate for nearest subspace classifier, Recursive aggregation of estimators by the mirror descent algorithm with averaging, Multiclass Boosting Algorithms for Shrinkage Estimators of Class Probability, A STUDY ON THE ERROR OF DISTRIBUTED ALGORITHMS FOR BIG DATA CLASSIFICATION WITH SVM, The asymptotics of ranking algorithms, Generalization Bounds for Some Ordinal Regression Algorithms, Refined Rademacher Chaos Complexity Bounds with Applications to the Multikernel Learning Problem, An empirical comparison of learning algorithms for nonparametric scoring: the \textsc{TreeRank} algorithm and other methods, Robust Support Vector Machines for Classification with Nonconvex and Smooth Losses, Learning Rates for Classification with Gaussian Kernels, On the consistency of multi-label learning, Boosting Method for Local Learning in Statistical Pattern Recognition, Optimal learning with \textit{Q}-aggregation, Convergence analysis of online algorithms, Simultaneous adaptation to the margin and to complexity in classification, Optimal rates of aggregation in classification under low noise assumption, Unnamed Item, On the rate of convergence for multi-category classification based on convex losses, Surprising properties of dropout in deep networks, Approximation with polynomial kernels and SVM classifiers, Unnamed Item, Unnamed Item, Unnamed Item, Supervised Learning by Support Vector Machines, Rademacher Chaos Complexities for Learning the Kernel Problem, Variance-based regularization with convex objectives, Multicategory large margin classification methods: hinge losses vs. coherence functions, Nonparametric Conditional Density Estimation Using Piecewise-Linear Solution Path of Kernel Quantile Regression, Regularized outcome weighted subgroup identification for differential treatment effects, Comment, Measuring the Capacity of Sets of Functions in the Analysis of ERM, Theory of Classification: a Survey of Some Recent Advances, Boosting in the Presence of Outliers: Adaptive Classification With Nonconvex Loss Functions, On Reject and Refine Options in Multicategory Classification, Learning rates of gradient descent algorithm for classification, Large‐margin classification with multiple decision rules, On the Optimality of Sample-Based Estimates of the Expectation of the Empirical Minimizer, FAST RATES FOR ESTIMATION ERROR AND ORACLE INEQUALITIES FOR MODEL SELECTION, Robust penalized logistic regression with truncated loss functions, Another Look at Distance-Weighted Discrimination, Confidence sets with expected sizes for Multiclass Classification, Online regularized generalized gradient classification algorithms, Unnamed Item, Unnamed Item, Square root penalty: Adaption to the margin in classification and in edge estimation, Learning Individualized Treatment Rules for Multiple-Domain Latent Outcomes, Unnamed Item, Unnamed Item, Unnamed Item, Complexities of convex combinations and bounding the generalization error in classification, Local Rademacher complexities, Boosting with early stopping: convergence and consistency, Comparison theorems on large-margin learning, Optimization by Gradient Boosting, Probability estimation with machine learning methods for dichotomous and multicategory outcome: Theory, Estimating Individualized Treatment Rules Using Outcome Weighted Learning, On the Effect and Remedies of Shrinkage on Classification Probability Estimation
