Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures.
Paul ViallardRémi EmonetAmaury HabrardEmilie MorvantValentina ZantedeschiPublished in: CoRR (2024)
Keyphrases
- generalization bounds
- pac bayes
- large deviations
- statistical learning theory
- learning theory
- data dependent
- generalization ability
- convex combinations
- model selection
- learning problems
- vc dimension
- linear classifiers
- ranking algorithm
- risk bounds
- theoretical framework
- statistical learning
- uniform convergence
- empirical risk minimization
- ranking functions
- bp neural network
- kernel machines
- neural network
- learning machines
- markov random field
- inductive inference
- function classes
- reinforcement learning
- machine learning