Convergence of flow-based generative models via proximal gradient descent in Wasserstein space.
Xiuyuan ChengJianfeng LuYixin TanYao XiePublished in: CoRR (2023)
Keyphrases
- generative model
- probabilistic model
- mixture model
- em algorithm
- discriminative models
- prior knowledge
- discriminative learning
- hierarchical hidden markov models
- conditional random fields
- machine learning
- expectation maximization
- object categories
- semi supervised
- loss function
- hidden variables
- maximum entropy principle
- mixed membership
- discriminatively trained
- generative and discriminative models
- image processing