Generative models · MLD-1086
Score matching
Learning a distribution's score, often through denoising objectives that avoid computing its normalization constant.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Train a score-based generative model.
Original caveat
Estimated scores need not define an accurately normalized density.
Context and aliases
Level: Advanced. Stages: Architecture · Training · Inference.
Tags: DL · Generative AI · Vision.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Denoising Diffusion Probabilistic Models ↗ · Consulted
- Deep Learning: online textbook ↗ · Consulted
- Flow Matching for Generative Modeling ↗ · Consulted
- Auto-Encoding Variational Bayes ↗ · Consulted
- Original reference URL ↗