Simpler PAC-Bayesian bounds for hostile data

DOI10.1007/s10994-017-5690-0zbMath1464.62238arXiv1610.07193OpenAlexW2535170036MaRDI QIDQ1640576

Benjamin Guedj, Pierre Alquier

Publication date: 14 June 2018

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1610.07193

zbMATH Keywords

oracle inequalities\(f\)-divergencedependent and unbounded dataPAC-Bayesian theory

Mathematics Subject Classification ID

Bayesian inference (62F15) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (3)

Exponential inequalities for nonstationary Markov chains ⋮ User-friendly Introduction to PAC-Bayes Bounds ⋮ High-dimensional VAR with low-rank transition

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Geometric median and robust estimation in Banach spaces
• Model selection for weakly dependent time series forecasting
• Sub-Gaussian mean estimators
• Robust linear least squares regression
• Aggregation of predictors for nonstationary sub-linear processes and online adaptive forecasting of time varying autoregressive processes
• Mixing: Properties and examples
• Rates of convergence for empirical processes of stationary mixing sequences
• Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.
• Challenging the empirical mean and empirical variance: a deviation study
• PAC-Bayesian estimation and prediction in sparse additive models
• Asymptotic theory of weakly dependent stochastic processes
• Fast learning rates in statistical inference through aggregation
• Concentration inequalities for dependent random variables via the martingale method
• Weak dependence. With examples and applications.
• Learning without Concentration
• Generalization Bounds for Time Series Prediction with Non-stationary Processes
• On the properties of variational approximations of Gibbs posteriors
• The Generalization Ability of Online Algorithms for Dependent Data
• PAC-Bayesian Inequalities for Martingales
• PAC-Bayesian Generalisation Error Bounds for Gaussian Process Classification
• A theory of the learnable
• Memory-universal prediction of stationary random processes
• Prediction of time series by statistical learning: general losses and fast rates
• Information Theory and Statistics: A Tutorial

This page was built for publication: Simpler PAC-Bayesian bounds for hostile data