Optimization and training dynamics · MLD-0008
Acquisition function
A rule scoring where to evaluate next in Bayesian optimization.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Balance predicted improvement against uncertainty.
Original caveat
Its behavior depends on surrogate uncertainty quality.
Context and aliases
Level: Intermediate. Stages: Training · Theory.
Tags: ML · DL · SLM · LLM.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- PyTorch optimization algorithms ↗ · Reference link
- PyTorch documentation ↗ · Reference link
- Original reference URL ↗