Optimization and training dynamics · MLD-0612
L-BFGS
A quasi-Newton optimizer using limited curvature history.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Fit a small smooth optimization problem.
Original caveat
It can be awkward with noisy mini-batch objectives.
Context and aliases
Level: Intermediate. Stages: Training · Theory.
Tags: ML · DL · SLM · LLM.
Aliases: Limited-memory Broyden-Fletcher-Goldfarb-Shanno.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- PyTorch optimization algorithms ↗ · Reference link
- PyTorch documentation ↗ · Reference link
- Original reference URL ↗