PAC-Bayesian stochastic model selection

DOI10.1023/A:1021840411064zbMath1056.68122MaRDI QIDQ1397414

David Allen McAllester

Publication date: 6 August 2003

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

Full work available at URL: https://doi.org/10.1023/a:1021840411064

zbMATH Keywords

posterior distribution; Gibbs distribution; PAC learning; model averaging; PAC-Baysian learning

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

Related Items

Unnamed Item, Unnamed Item, Unnamed Item, Minimum description length revisited, On the measurement complexity of differentially private query answering, Joint production in stochastic non-parametric envelopment of data with firm-specific directions, Human action segmentation and recognition using discriminative semi-Markov models, Sparse regression learning by aggregation and Langevin Monte-Carlo, Mirror averaging with sparsity priors, Challenging the empirical mean and empirical variance: a deviation study, A computational learning theory of active object recognition under uncertainty, Learning the set covering machine by bound minimization and margin-sparsity trade-off, Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices, Fast greedy \(\mathcal{C} \)-bound minimization with guarantees, PAC-Bayes Bounds for Supervised Classification, Robust Algorithms via PAC-Bayes and Laplace Distributions, What Can We Learn Privately?, Theory of Classification: a Survey of Some Recent Advances