Regularization and generalization · MLD-0335
Double descent
A pattern where test error rises near interpolation and later falls as capacity or training increases.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Study model size versus test error.
Original caveat
It is an observed pattern in some settings, not a universal law.
Context and aliases
Level: Intermediate. Stages: Theory · Training · Evaluation.
Tags: ML · DL · SLM · LLM.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- Google Machine Learning Glossary ↗ · Consulted
- PyTorch neural-network layers ↗ · Reference link
- Original reference URL ↗