Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.

DOI10.1007/B99352zbMath1076.93002OpenAlexW138682821MaRDI QIDQ1880598

Olivier Catoni

Publication date: 30 September 2004

Published in: Lecture Notes in Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/b99352

zbMATH Keywords

pattern recognitionMarkov chainssimulated annealingprobability distributioncoding theoryestimatorsoracle inequalitiesstatistical learningKullback divergencerisk functionleast-squares regressionadaptive classificationGibbs estimators

Mathematics Subject Classification ID

Markov processes: estimation; hidden Markov models (62M05) Stochastic programming (90C15) Estimation and detection in stochastic control theory (93E10) Least squares and related methods for stochastic control systems (93E24) Pattern recognition, speech recognition (68T10) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Research exposition (monographs, survey articles) pertaining to systems and control theory (93-02) Stochastic learning and adaptive control (93E35) Statistical aspects of information-theoretic topics (62B10) Nonparametric inference (62G99)

Related Items (65)

On aggregation for heavy-tailed classes ⋮ Performance of empirical risk minimization in linear aggregation ⋮ PAC-Bayesian lifelong learning for multi-armed bandits ⋮ Sparsity in penalized empirical risk minimization ⋮ 1-bit matrix completion: PAC-Bayesian analysis of a variational approximation ⋮ Simpler PAC-Bayesian bounds for hostile data ⋮ PAC-Bayesian high dimensional bipartite ranking ⋮ Fast learning rates in statistical inference through aggregation ⋮ Mixing partially linear regression models ⋮ A general procedure to combine estimators ⋮ Ordered smoothers with exponential weighting ⋮ An oracle inequality for quasi-Bayesian nonnegative matrix factorization ⋮ Exponential weighting and oracle inequalities for projection estimates ⋮ Challenging the empirical mean and empirical variance: a deviation study ⋮ \(\ell _{1}\)-regularized linear regression: persistence and oracle inequalities ⋮ Aggregation of predictors for nonstationary sub-linear processes and online adaptive forecasting of time varying autoregressive processes ⋮ Random design analysis of ridge regression ⋮ A reduced-rank approach to predicting multiple binary responses through machine learning ⋮ Robust estimation in controlled branching processes: Bayesian estimators via disparities ⋮ Sharp oracle inequalities for aggregation of affine estimators ⋮ From robust tests to Bayes-like posterior distributions ⋮ Concentration of tempered posteriors and of their variational approximations ⋮ Aggregation of estimators and stochastic optimization ⋮ Gibbs posterior concentration rates under sub-exponential type losses ⋮ Oracle inequalities for cross-validation type procedures ⋮ PAC-Bayesian estimation and prediction in sparse additive models ⋮ Sparse regression learning by aggregation and Langevin Monte-Carlo ⋮ PAC-Bayesian bounds for sparse regression estimation with exponential weights ⋮ On the optimality of the aggregate with exponential weights for low temperatures ⋮ Model selection for weakly dependent time series forecasting ⋮ Mirror averaging with sparsity priors ⋮ Kullback-Leibler aggregation and misspecified generalized linear models ⋮ Estimator selection with respect to Hellinger-type risks ⋮ A general framework for Bayes structured linear models ⋮ Concentration inequalities for the exponential weighting method ⋮ Aggregation of affine estimators ⋮ Bayesian fractional posteriors ⋮ Aggregation for Gaussian regression ⋮ Simultaneous adaptation to the margin and to complexity in classification ⋮ Spatial aggregation of local likelihood estimates with applications to classification ⋮ Optimal rates of aggregation in classification under low noise assumption ⋮ Pseudo-Bayesian quantum tomography with rank-adaptation ⋮ Unnamed Item ⋮ Learning by mirror averaging ⋮ Prediction of time series by statistical learning: general losses and fast rates ⋮ On some recent advances on high dimensional Bayesian statistics ⋮ A quasi-Bayesian perspective to online clustering ⋮ Leave Pima Indians alone: binary regression as a benchmark for Bayesian computation ⋮ Iterative feature selection in least square regression estimation ⋮ Sparse estimation by exponential weighting ⋮ A universal procedure for aggregating estimators ⋮ Generalized mirror averaging and \(D\)-convex aggregation ⋮ Linear and convex aggregation of density estimators ⋮ On the exponentially weighted aggregate with the Laplace prior ⋮ Robust forecast combinations ⋮ Flexible, boundary adapted, nonparametric methods for the estimation of univariate piecewise-smooth functions ⋮ Theory of Classification: a Survey of Some Recent Advances ⋮ Sparse recovery in convex hulls via entropy penalization ⋮ KFC: A clusterwise supervised learning procedure based on the aggregation of distances ⋮ Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions ⋮ Aggregation using input-output trade-off ⋮ Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices ⋮ A minimax framework for quantifying risk-fairness trade-off in regression ⋮ A Bayesian approach for noisy matrix completion: optimal rate under general sampling distribution ⋮ Model selection for regression on a random design

This page was built for publication: Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.