Foundations · MLD-0457

Generalization

A model's ability to perform well on data beyond its training examples.

Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.

Original example

Maintain accuracy on newly collected samples.

Original caveat

Held-out performance only reflects the tested distribution.

Context and aliases

Level: Foundational. Stages: Theory · Training · Inference.

Tags: ML · DL · SLM · LLM.

Aliases: None recorded.

Related concepts

Overfitting
Distribution shift

Concepts linking here

Expected risk
External validity
Grokking
Implicit regularization
No-free-lunch theorem
Overfitting
PAC learning
Sample complexity
Shortcut learning

Original references

Deep Learning: online textbook ↗ · Consulted
Google Machine Learning Glossary ↗ · Consulted
Original reference URL ↗

Open original record, export or annotate →