Optimization and training dynamics · MLD-0737
Mini-batch
A subset of training examples processed together for an update or gradient estimate.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Process 64 images at once.
Original caveat
A microbatch may be smaller than the effective update batch.
Context and aliases
Level: Foundational. 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 ↗