Pages that link to "Item:Q5754926"

The following pages link to Convexity, Classification, and Risk Bounds (Q5754926):

Displaying 50 items.

• Consistency of support vector machines for forecasting the evolution of an unknown ergodic dynamical system from observations with unknown noise (Q1020982) (← links)
• On surrogate loss functions and \(f\)-divergences (Q1020983) (← links)
• Convergence rates of generalization errors for margin-based classification (Q1021988) (← links)
• Gradient learning in a classification setting by gradient descent (Q1048984) (← links)
• Learning from binary labels with instance-dependent noise (Q1631810) (← links)
• Semi-supervised AUC optimization based on positive-unlabeled learning (Q1640567) (← links)
• Fast learning rate of non-sparse multiple kernel learning and optimal regularization strategies (Q1657947) (← links)
• Projected estimators for robust semi-supervised classification (Q1697918) (← links)
• Query-dependent ranking and its asymptotic properties (Q1722064) (← links)
• Calibration of \(\epsilon\)-insensitive loss in support vector machines regression (Q1730072) (← links)
• Cost-sensitive feature selection for support vector machines (Q1734839) (← links)
• Bounding the difference between RankRC and RankSVM and application to multi-level rare class kernel ranking (Q1741234) (← links)
• Robust multicategory support vector machines using difference convex algorithm (Q1749454) (← links)
• Stochastic margin-based structure learning of Bayesian network classifiers (Q1760416) (← links)
• A note on margin-based loss functions in classification (Q1770065) (← links)
• Deformation of log-likelihood loss function for multiclass boosting (Q1784701) (← links)
• \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities (Q1930861) (← links)
• Boosting \(k\)-NN for categorization of natural scenes (Q1943405) (← links)
• Calibrated asymmetric surrogate losses (Q1950846) (← links)
• Oracle inequalities for cross-validation type procedures (Q1950881) (← links)
• Upper bounds and aggregation in bipartite ranking (Q1951156) (← links)
• Penalized empirical risk minimization over Besov spaces (Q1952004) (← links)
• Self-concordant analysis for logistic regression (Q1952060) (← links)
• Fast learning of relational kernels (Q1959554) (← links)
• Multiclass classification, information, divergence and surrogate risk (Q1990579) (← links)
• Multicategory classification via forward-backward support vector machine (Q2006962) (← links)
• Surrogate losses in passive and active learning (Q2008623) (← links)
• Sentiment analysis with covariate-assisted word embeddings (Q2044406) (← links)
• SVM-boosting based on Markov resampling: theory and algorithm (Q2057733) (← links)
• Nonregular and minimax estimation of individualized thresholds in high dimension with binary responses (Q2091840) (← links)
• Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling (Q2112261) (← links)
• A no-free-lunch theorem for multitask learning (Q2112800) (← links)
• Estimating individualized treatment rules for treatments with hierarchical structure (Q2136622) (← links)
• Convergence rates of deep ReLU networks for multiclass classification (Q2137813) (← links)
• Learning rates of kernel-based robust classification (Q2157879) (← links)
• Convergence rates for empirical barycenters in metric spaces: curvature, convexity and extendable geodesics (Q2182123) (← links)
• Principled analytic classifier for positive-unlabeled learning via weighted integral probability metric (Q2183591) (← links)
• Learning rates for the kernel regularized regression with a differentiable strongly convex loss (Q2191832) (← links)
• Quantitative convergence analysis of kernel based large-margin unified machines (Q2191836) (← links)
• Learning with mitigating random consistency from the accuracy measure (Q2217414) (← links)
• Classification with label noise: a Markov chain sampling framework (Q2218376) (← links)
• Finite-sample analysis of \(M\)-estimators using self-concordance (Q2219231) (← links)
• Discriminative training of conditional random fields with probably submodular constraints (Q2226189) (← links)
• Calibration and regret bounds for order-preserving surrogate losses in learning to rank (Q2251435) (← links)
• Convergence rates of learning algorithms by random projection (Q2252501) (← links)
• Robustness of learning algorithms using hinge loss with outlier indicators (Q2292231) (← links)
• Regularized ranking with convex losses and \(\ell^1\)-penalty (Q2319268) (← links)
• Sample average approximation with sparsity-inducing penalty for high-dimensional stochastic programming (Q2330643) (← links)
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder) (Q2373576) (← links)
• The new interpretation of support vector machines on statistical learning theory (Q2379242) (← links)