Classification with Gaussians and convex loss

zbMATH Open1235.68207MaRDI QIDQ2880932FDOQ2880932

Authors: Dao-Hong Xiang, Ding-Xuan Zhou 

Publication date: 17 April 2012

Published in: Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL: http://www.jmlr.org/papers/v10/xiang09a.html

Recommendations

• Classification with Gaussians and convex loss. II: Improving error bounds by noise conditions
• Convexity, Classification, and Risk Bounds
• Learning with convex loss and indefinite kernels
• scientific article; zbMATH DE number 1140602
• Optimal learning with Gaussians and correntropy loss
• Analysis to Neyman-Pearson classification with convex loss function
• High-dimensional regression and classification under a class of convex loss functions
• Convex calibration dimension for multiclass loss matrices
• Convex surrogate minimization in classification
• On the rate of convergence for multi-category classification based on convex losses

zbMATH Keywords

reproducing kernel Hilbert spacebinary classificationapproximationcovering numbergeneral convex lossvarying Gaussian kernels

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Cited In (30)

• Logistic classification with varying gaussians
• Learning rates for the risk of kernel-based quantile regression estimators in additive models
• Calibration of \(\epsilon\)-insensitive loss in support vector machines regression
• Analysis to Neyman-Pearson classification with convex loss function
• Classification with Gaussians and convex loss. II: Improving error bounds by noise conditions
• Online classification with varying Gaussians
• Covering numbers of Gaussian reproducing kernel Hilbert spaces
• Learning with Convex Loss and Indefinite Kernels
• Employing different loss functions for the classification of images via supervised learning
• Binning in Gaussian kernel regularization
• Large margin unified machines with non-i.i.d. process
• A Note on Support Vector Machines with Polynomial Kernels
• Quantile regression with \(\ell_1\)-regularization and Gaussian kernels
• Multi-kernel regularized classifiers
• Learning rates of regression with \(q\)-norm loss and threshold
• Distributed regularized least squares with flexible Gaussian kernels
• Unregularized online algorithms with varying Gaussians
• Comparison theorems on large-margin learning
• Learning rates of kernel-based robust classification
• Convergence analysis for complementary-label learning with kernel ridge regression
• Conditional quantiles with varying Gaussians
• Learnability of Gaussians with flexible variances
• Learning with sample dependent hypothesis spaces
• Optimal regression rates for SVMs using Gaussian kernels
• A new comparison theorem on conditional quantiles
• An oracle inequality for regularized risk minimizers with strongly mixing observations
• Learning Rates for Classification with Gaussian Kernels
• Learning from non-identical sampling for classification
• A STUDY ON THE ERROR OF DISTRIBUTED ALGORITHMS FOR BIG DATA CLASSIFICATION WITH SVM
• Optimal learning with Gaussians and correntropy loss

This page was built for publication: Classification with Gaussians and convex loss

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2880932)