Optimization and training dynamics · MLD-0533
Hyperband
A resource-allocation strategy using repeated successive-halving schedules.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Stop poor hyperparameter trials early.
Original caveat
Early performance must be informative about later performance.
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 ↗