Learning by mirror averaging

DOI10.1214/07-AOS546zbMath1274.62288arXivmath/0511468MaRDI QIDQ955138

Philippe Rigollet, Alexandre B. Tsybakov, Anatoli B. Juditsky

Publication date: 18 November 2008

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/math/0511468

zbMATH Keywords

aggregation; stochastic optimization; model selection; learning; oracle inequalities; mirror averaging

Mathematics Subject Classification ID

62G08: Nonparametric regression and quantile regression

62G20: Asymptotic properties of nonparametric inference

62G05: Nonparametric estimation

62C20: Minimax procedures in statistical decision theory

Related Items

Generalized mirror averaging and \(D\)-convex aggregation, Parameter tuning in pointwise adaptation using a propagation approach, Aggregation via empirical risk minimization, A universal procedure for aggregating estimators, Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity, Fast learning rates in statistical inference through aggregation, Aggregation for Gaussian regression, Optimal rates of aggregation in classification under low noise assumption

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• From \(\varepsilon\)-entropy to KL-entropy: analysis of minimum information complexity density estima\-tion
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Model selection in nonparametric regression
• Mixing strategies for density estimation.
• Complexity regularization via localized random penalties
• Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.
• Recursive aggregation of estimators by the mirror descent algorithm with averaging
• Aggregation for Gaussian regression
• Spatial aggregation of local likelihood estimates with applications to classification
• Universal linear prediction by model order weighting
• Theory of Classification: a Survey of Some Recent Advances
• Information Theory and Mixing Least-Squares Regressions
• Sequential Procedures for Aggregating Arbitrary Estimators of a Conditional Mean
• Efficient agnostic learning of neural networks with bounded fan-in
• Sequential prediction of individual sequences under general loss functions
• Competitive On-line Statistics
• Learning Theory and Kernel Machines
• Prediction, Learning, and Games
• Introduction to nonparametric estimation
• Model selection and error estimation