Fast rates for general unbounded loss functions: from ERM to generalized Bayes

zbMATH Open1498.68238arXiv1605.00252MaRDI QIDQ4969103FDOQ4969103

Authors: Peter D. Grünwald, Nishant A. Mehta 

Publication date: 5 October 2020

Full work available at URL: https://arxiv.org/abs/1605.00252

Recommendations

• Posterior concentration and fast convergence rates for generalized Bayesian learning
• Relative deviation learning bounds and generalization with unbounded loss functions
• Fast rates in statistical and online learning
• Risk bounds for statistical learning
• Fast learning rates in statistical inference through aggregation

zbMATH Keywords

misspecificationfast ratesstatistical learning theorygeneralized BayesPAC-Bayes

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Bayesian inference (62F15) Density estimation (62G07) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Empirical Bayes posterior concentration in sparse high-dimensional linear models
• Title not available (Why is that?)
• Fast learning rates in statistical inference through aggregation
• Optimal learning with \textit{Q}-aggregation
• Title not available (Why is that?)
• Prediction, Learning, and Games
• On Information and Sufficiency
• Learning by mirror averaging
• Bayesian fractional posteriors
• Convergence rates of posterior distributions for non iid observations
• Convergence rates of posterior distributions.
• Challenging the empirical mean and empirical variance: a deviation study
• Loss minimization and parameter estimation with heavy tails
• Title not available (Why is that?)
• Convex Analysis
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Misspecification in infinite-dimensional Bayesian statistics
• Local Rademacher complexities
• Minimum contrast estimators on sieves: Exponential bounds and rates of convergence
• Inconsistency of Bayesian inference for misspecified linear models, and a proposal for repairing it
• Minimum complexity density estimation
• Robust Bayesian inference via coarsening
• A General Framework for Updating Belief Distributions
• Nonparametric Bayesian model selection and averaging
• The semiparametric Bernstein-von Mises theorem
• Mutual information, metric entropy and cumulative relative entropy risk
• Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory
• The consistency of posterior distributions in nonparametric problems
• On Bayesian consistency
• Title not available (Why is that?)
• Optimal aggregation of classifiers in statistical learning.
• Probability inequalities for likelihood ratios and convergence rates of sieve MLEs
• Learning without concentration
• 10.1162/1532443041424300
• Fast learning rates for plug-in classifiers
• Model selection for Gaussian regression with random design
• Rényi Divergence and Kullback-Leibler Divergence
• Information-theoretic determination of minimax rates of convergence
• Title not available (Why is that?)
• Efficient agnostic learning of neural networks with bounded fan-in
• Empirical minimization
• An asymptotic property of model selection criteria
• Follow the leader if you can, hedge if you must
• PAC-Bayesian stochastic model selection
• From \(\varepsilon\)-entropy to KL-entropy: analysis of minimum information complexity density estima\-tion
• A decision-theoretic extension of stochastic complexity and its applications to learning
• Rigorous learning curve bounds from statistical mechanics
• $f$ -Divergence Inequalities
• Information Consistency of Nonparametric Gaussian Process Methods
• Relative deviation learning bounds and generalization with unbounded loss functions
• On aggregation for heavy-tailed classes
• Fast rates in statistical and online learning
• The safe Bayesian. Learning the learning rate via the mixability gap
• Regularization, sparse recovery, and median-of-means tournaments

Cited In (17)

• Generalized Bayes approach to inverse problems with model misspecification
• Anytime-Valid Tests of Conditional Independence Under Model-X
• ERM learning with unbounded sampling
• Relative deviation learning bounds and generalization with unbounded loss functions
• Empirical Bayes inference in sparse high-dimensional generalized linear models
• Posterior consistency for the spectral density of non‐Gaussian stationary time series
• Minimax rates for conditional density estimation via empirical entropy
• Relaxing the i.i.d. assumption: adaptively minimax optimal regret via root-entropic regularization
• The no-free-lunch theorems of supervised learning
• Fast rates in statistical and online learning
• A comparison of learning rate selection methods in generalized Bayesian inference
• Bayesian functional registration of fMRI activation maps
• Posterior concentration and fast convergence rates for generalized Bayesian learning
• Gibbs posterior concentration rates under sub-exponential type losses
• Bernstein-von Mises theorem and misspecified models: a review
• Gibbs posterior convergence and the thermodynamic formalism
• User-friendly Introduction to PAC-Bayes Bounds

This page was built for publication: Fast rates for general unbounded loss functions: from ERM to generalized Bayes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4969103)