Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation.
Tuan LeJulian CremerFrank NoéDjork-Arné ClevertKristof SchüttPublished in: CoRR (2023)
Keyphrases
- generative model
- design space
- probabilistic model
- design process
- discriminative models
- mixture model
- discriminative learning
- em algorithm
- design space exploration
- maximum entropy principle
- conditional random fields
- search space
- prior knowledge
- graphical models
- generative and discriminative models
- hierarchical hidden markov models
- representational power
- design tools
- expectation maximization
- semi supervised
- object categories
- topic models
- reinforcement learning
- language model
- bayesian networks
- data sets