Generative models · MLD-1018
Reparameterization trick
Expressing a random sample as a differentiable transformation of parameters and parameter-free noise.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Backpropagate through Gaussian latent samples.
Original caveat
Not every distribution admits the same simple reparameterization.
Context and aliases
Level: Advanced. Stages: Architecture · Training · Inference.
Tags: DL · Generative AI · Vision.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- Auto-Encoding Variational Bayes ↗ · Consulted
- Original reference URL ↗