A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks.
Renjie LiaoRaquel UrtasunRichard S. ZemelPublished in: CoRR (2020)
Keyphrases
- generalization bounds
- vc dimension
- neural network
- pac bayesian
- data dependent
- learning theory
- model selection
- upper bound
- generalization ability
- ranking algorithm
- statistical learning theory
- sample complexity
- pattern recognition
- artificial neural networks
- sample size
- linear classifiers
- uniform convergence
- concept classes
- ranking functions
- inductive inference
- learning problems
- fuzzy logic
- cross validation
- back propagation
- lower bound
- training process
- bp neural network
- neural network model
- special case
- search engine
- learning algorithm