Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels.
Alexander ImmerTycho F. A. van der OuderaaMark van der WilkGunnar RätschBernhard SchölkopfPublished in: ICML (2023)
Keyphrases
- marginal likelihood
- model selection
- gaussian process
- closed form
- neural network
- information criterion
- hyperparameters
- exponential family
- monte carlo
- kernel function
- gaussian processes
- kernel methods
- bayesian information criterion
- approximate inference
- multiple kernel learning
- random variables
- cross validation
- graphical models
- machine learning
- maximum likelihood
- bayesian inference
- image reconstruction
- sample size