A PAC-Bayesian margin bound for linear classifiers

DOI10.1109/TIT.2002.805090zbMath1063.62092MaRDI QIDQ4677637

Ralf Herbrich, Thore Graepel

Publication date: 11 May 2005

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Mathematics Subject Classification ID

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

Related Items

CORRELATION-BASED MULTIDIMENSIONAL SCALING FOR UNSUPERVISED SUBSPACE LEARNING ⋮ The new interpretation of support vector machines on statistical learning theory ⋮ 1-bit matrix completion: PAC-Bayesian analysis of a variational approximation ⋮ Invariant kernel functions for pattern analysis and machine learning ⋮ Kernels as features: on kernels, margins, and low-dimensional mappings ⋮ Bayesian Classification of Tumours by Using Gene Expression Data ⋮ Binet-Cauchy kernels on dynamical systems and its application to the analysis of dynamic scenes ⋮ Incremental learning algorithm for large-scale semi-supervised ordinal regression ⋮ Maximizing upgrading and downgrading margins for ordinal regression ⋮ A reduced-rank approach to predicting multiple binary responses through machine learning ⋮ PAC-Bayesian framework based drop-path method for 2D discriminative convolutional network pruning ⋮ User-friendly Introduction to PAC-Bayes Bounds ⋮ New and efficient DCA based algorithms for minimum sum-of-squares clustering ⋮ The \(K\)-armed dueling bandits problem ⋮ Support vector machines with applications ⋮ Kernel methods in machine learning ⋮ On the rate of convergence for multi-category classification based on convex losses ⋮ A one-dimensional analysis for the probability of error of linear classifiers for normally distributed classes ⋮ PAC-Bayesian compression bounds on the prediction error of learning algorithms for classification ⋮ PAC-Bayesian compression bounds on the prediction error of learning algorithms for classification ⋮ Robust Algorithms via PAC-Bayes and Laplace Distributions ⋮ A theory of learning with similarity functions