Generative models · MLD-0385
Evidence lower bound
An optimizable lower bound on log evidence, balancing expected data fit against divergence from a prior.
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 variational autoencoder.
Original caveat
A tighter bound is not automatically a better downstream representation.
Context and aliases
Level: Advanced. Stages: Architecture · Training · Inference.
Tags: DL · Generative AI · Vision.
Aliases: ELBO.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- Auto-Encoding Variational Bayes ↗ · Consulted
- Original reference URL ↗