Fast learning rates in statistical inference through aggregation
From MaRDI portal
Publication:2388975
DOI10.1214/08-AOS623zbMath1360.62167arXiv0909.1468OpenAlexW4302040898MaRDI QIDQ2388975
Publication date: 22 July 2009
Published in: The Annals of Statistics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/0909.1468
aggregationstatistical learningminimax lower boundsfast rates of convergenceconvex lossexcess risk\(L_q\)-regressionlower bounds in VC-classes
Nonparametric regression and quantile regression (62G08) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)
Related Items
On aggregation for heavy-tailed classes ⋮ Simpler PAC-Bayesian bounds for hostile data ⋮ Fast learning rates in statistical inference through aggregation ⋮ Unnamed Item ⋮ Exponential weights in multivariate regression and a low-rankness favoring prior ⋮ Aggregation of predictors for nonstationary sub-linear processes and online adaptive forecasting of time varying autoregressive processes ⋮ Variance function estimation in regression model via aggregation procedures ⋮ User-friendly Introduction to PAC-Bayes Bounds ⋮ On the optimality of the empirical risk minimization procedure for the convex aggregation problem ⋮ Relaxing the i.i.d. assumption: adaptively minimax optimal regret via root-entropic regularization ⋮ Empirical risk minimization is optimal for the convex aggregation problem ⋮ PAC-Bayesian estimation and prediction in sparse additive models ⋮ Upper bounds and aggregation in bipartite ranking ⋮ Sparse regression learning by aggregation and Langevin Monte-Carlo ⋮ On the optimality of the aggregate with exponential weights for low temperatures ⋮ Mirror averaging with sparsity priors ⋮ Optimal learning with \textit{Q}-aggregation ⋮ Unnamed Item ⋮ Active Nearest-Neighbor Learning in Metric Spaces ⋮ Prediction of time series by statistical learning: general losses and fast rates ⋮ Optimal learning with Bernstein Online Aggregation ⋮ A quasi-Bayesian perspective to online clustering ⋮ On the exponentially weighted aggregate with the Laplace prior ⋮ Unnamed Item ⋮ Exact lower bounds for the agnostic probably-approximately-correct (PAC) machine learning model ⋮ Suboptimality of constrained least squares and improvements via non-linear predictors ⋮ Distribution-free robust linear regression
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- How to better use expert advice
- Iterative feature selection in least square regression estimation
- Learning by mirror averaging
- Fast learning rates for plug-in classifiers
- Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
- Central limit theorems for empirical measures
- A game of prediction with expert advice
- Information-theoretic determination of minimax rates of convergence
- Combining different procedures for adaptive regression
- Smooth discrimination analysis
- On prediction of individual sequences
- Lower bounds for the rate of convergence in nonparametric pattern recognition
- The progressive mixture estimator for regression trees.
- Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.
- Optimal aggregation of classifiers in statistical learning.
- Aggregated estimators and empirical complexity for least square regression
- Measuring mass concentrations and estimating density contour clusters -- An excess mass approach
- Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
- Fast learning rates in statistical inference through aggregation
- Simultaneous adaptation to the margin and to complexity in classification
- Optimal rates of aggregation in classification under low noise assumption
- [https://portal.mardi4nfdi.de/wiki/Publication:3048064 Estimation des densit�s: risque minimax]
- Theory of Classification: a Survey of Some Recent Advances
- A New Lower Bound for Multiple Hypothesis Testing
- On the Generalization Ability of On-Line Learning Algorithms
- Information-theoretic upper and lower bounds for statistical estimation
- Sequential Procedures for Aggregating Arbitrary Estimators of a Conditional Mean
- Any Discrimination Rule Can Have an Arbitrarily Bad Probability of Error for Finite Sample Size
- How to use expert advice
- Sequential prediction of individual sequences under general loss functions
- Universal prediction
- [https://portal.mardi4nfdi.de/wiki/Publication:4743580 Approximation dans les espaces m�triques et th�orie de l'estimation]
- Learning Theory and Kernel Machines
- Suboptimality of Penalized Empirical Risk Minimization in Classification
- Prediction, Learning, and Games
- Learning Theory
- Learning Theory
- Introduction to nonparametric estimation
- Combinatorial methods in density estimation
- Some applications of concentration inequalities to statistics
