Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures.
Paul ViallardRémi EmonetAmaury HabrardEmilie MorvantValentina ZantedeschiPublished in: AISTATS (2024)
Keyphrases
- generalization bounds
- pac bayes
- large deviations
- statistical learning theory
- learning theory
- data dependent
- generalization ability
- risk bounds
- vc dimension
- convex combinations
- model selection
- linear classifiers
- ranking algorithm
- learning problems
- theoretical framework
- empirical risk minimization
- statistical learning
- machine learning
- uniform convergence
- ranking functions
- ensemble learning
- learning machines
- support vector machine
- markov random field
- upper bound
- feature extraction
- training data
- active learning
- bp neural network
- learning tasks
- multi class