scientific article

zbMATH Open1277.62015arXiv0712.0248MaRDI QIDQ3623263FDOQ3623263

Authors: Olivier Catoni 

Publication date: 16 April 2009

Full work available at URL: https://arxiv.org/abs/0712.0248

Title of this publication is not available (Why is that?)

Recommendations

• PAC-Bayes bounds for supervised classification
• Publication:4714288
• scientific article; zbMATH DE number 7272386
• scientific article; zbMATH DE number 1114411
• An introduction to some statistical aspects of PAC learning theory
• The peculiar statistical mechanics of optimal learning machines
• Nonequilibrium thermodynamics of self-supervised learning
• Thermodynamics of restricted Boltzmann machines and related learning dynamics
• scientific article; zbMATH DE number 7219345
• PAC-Bayesian compression bounds on the prediction error of learning algorithms for classification

zbMATH Keywords

support vector machinespattern recognitioneffective temperaturestatistical learning theoryrandomized estimatorsGibbs posterior distributionsPAC-Bayesian theoremscompression schemesmargin boundstransductive inferenceadaptive statisticslocal complexity boundsMammen and Tsybakov margin assumptionVapnik-Cervonenkis dimension

Mathematics Subject Classification ID

Bayesian inference (62F15) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Research exposition (monographs, survey articles) pertaining to statistics (62-02)

Cited In (61)

• Bayesian fractional posteriors
• Robust Bayes estimation using the density power divergence
• Fast greedy \(\mathcal{C} \)-bound minimization with guarantees
• On strict sub-Gaussianity, optimal proxy variance and symmetry for bounded random variables
• 1-bit matrix completion: PAC-Bayesian analysis of a variational approximation
• Robust Bayes-like estimation: rho-Bayes estimation
• Title not available (Why is that?)
• Title not available (Why is that?)
• Challenging the empirical mean and empirical variance: a deviation study
• Title not available (Why is that?)
• Optimal learning with \textit{Q}-aggregation
• Model selection by resampling penalization
• Concentration of tempered posteriors and of their variational approximations
• Oracle inequalities for cross-validation type procedures
• Scalable subspace methods for derivative-free nonlinear least-squares optimization
• Comment: Transductive PAC-Bayes bounds seen as a generalization of Vapnik-Chervonenkis bounds
• Exponential weights in multivariate regression and a low-rankness favoring prior
• A Bayesian approach for noisy matrix completion: optimal rate under general sampling distribution
• Sparse regression learning by aggregation and Langevin Monte-Carlo
• Sharp oracle inequalities for low-complexity priors
• Leave Pima Indians alone: binary regression as a benchmark for Bayesian computation
• Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions
• On some recent advances on high dimensional Bayesian statistics
• Mathematical analysis of a two-patch model of tuberculosis disease with staged progression
• Mirror averaging with sparsity priors
• Model selection for weakly dependent time series forecasting
• Simpler PAC-Bayesian bounds for hostile data
• PAC-Bayesian high dimensional bipartite ranking
• General inequalities for Gibbs posterior with nonadditive empirical risk
• Transductive versions of the Lasso and the Dantzig selector
• PAC-Bayesian bounds for sparse regression estimation with exponential weights
• PAC-Bayesian bounds for randomized empirical risk minimizers
• PAC-Bayesian estimation and prediction in sparse additive models
• An efficient adaptive MCMC algorithm for pseudo-Bayesian quantum tomography
• Chaining meets chain rule: multilevel entropic regularization and training of neural networks
• Consistency of variational Bayes inference for estimation and model selection in mixtures
• Estimation from nonlinear observations via convex programming with application to bilinear regression
• An oracle inequality for quasi-Bayesian nonnegative matrix factorization
• PAC-Bayes bounds for supervised classification
• The lower tail of random quadratic forms with applications to ordinary least squares
• Optimal learning with Bernstein online aggregation
• On the exponentially weighted aggregate with the Laplace prior
• On the optimality of the aggregate with exponential weights for low temperatures
• General Robust Bayes Pseudo-Posteriors: Exponential Convergence Results with Applications
• Robust and rate-optimal Gibbs posterior inference on the boundary of a noisy image
• Prediction of time series by statistical learning: general losses and fast rates
• Title not available (Why is that?)
• Title not available (Why is that?)
• PAC-Bayesian pattern classification with kernels. Theory, algorithms, and an application to the game Go.
• Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices
• Pseudo-Bayesian quantum tomography with rank-adaptation
• A quasi-Bayesian perspective to online clustering
• Sparse estimation by exponential weighting
• Gibbs posterior convergence and the thermodynamic formalism
• Entropic regularization of neural networks: self-similar approximations
• Covariance estimation under missing observations and \(L_4 - L_2\) moment equivalence
• Dimension-free bounds for sums of dependent matrices and operators with heavy-tailed distributions
• A reduced-rank approach to predicting multiple binary responses through machine learning
• PACMAN: PAC-style bounds accounting for the mismatch between accuracy and negative log-loss
• High-dimensional sparse classification using exponential weighting with empirical hinge loss
• User-friendly Introduction to PAC-Bayes Bounds

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3623263)