On the detrimental effect of invariances in the likelihood for variational inference.
Richard KurleRalf HerbrichTim JanuschowskiYuyang WangJan GasthausPublished in: CoRR (2022)
Keyphrases
- variational inference
- bayesian inference
- probabilistic graphical models
- topic models
- latent dirichlet allocation
- mixture model
- posterior distribution
- probabilistic model
- gaussian process
- closed form
- maximum likelihood
- variational methods
- exact inference
- machine learning
- exponential family
- posterior probability
- dimensionality reduction
- hyperparameters
- graphical models
- parameter estimation
- approximate inference
- higher order