Some PAC-Bayesian theorems

DOI10.1023/A:1007618624809zbMath0945.68157OpenAlexW4244569433MaRDI QIDQ1969323

David Allen McAllester

Publication date: 16 March 2000

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

Full work available at URL: https://doi.org/10.1023/a:1007618624809

zbMATH Keywords

PAC-Bayesian algorithms

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (28)

Generalization bounds for averaged classifiers ⋮ PAC-Bayesian lifelong learning for multi-armed bandits ⋮ PAC-Bayesian high dimensional bipartite ranking ⋮ Suboptimal behavior of Bayes and MDL in classification under misspecification ⋮ Mining evolving data streams for frequent patterns ⋮ Bayesian functional registration of fMRI activation maps ⋮ Challenging the empirical mean and empirical variance: a deviation study ⋮ Stochastic feature mapping for PAC-Bayes classification ⋮ Sim-to-lab-to-real: safe reinforcement learning with shielding and generalization guarantees ⋮ Consistent Sparse Deep Learning: Theory and Computation ⋮ Generalized Bayes Quantification Learning under Dataset Shift ⋮ Sharp oracle inequalities for aggregation of affine estimators ⋮ Unnamed Item ⋮ Unnamed Item ⋮ PAC-Bayesian estimation and prediction in sparse additive models ⋮ The false discovery rate for statistical pattern recognition ⋮ Dynamics of Bayesian updating with dependent data and misspecified models ⋮ PAC-Bayesian bounds for sparse regression estimation with exponential weights ⋮ Model selection for weakly dependent time series forecasting ⋮ Fast greedy \(\mathcal{C} \)-bound minimization with guarantees ⋮ Generalization Error in Deep Learning ⋮ Estimation from nonlinear observations via convex programming with application to bilinear regression ⋮ A quasi-Bayesian perspective to online clustering ⋮ Data preparation using data quality matrices for classification mining ⋮ Sparse recovery in convex hulls via entropy penalization ⋮ Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices ⋮ A Bayesian approach for noisy matrix completion: optimal rate under general sampling distribution ⋮ Gibbs posterior convergence and the thermodynamic formalism

This page was built for publication: Some PAC-Bayesian theorems