Statistics and experimental design · MLD-0247
Cross-validation
Repeated training and evaluation across data partitions to estimate performance or select configurations.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Use five folds for model selection.
Original caveat
All learned preprocessing belongs inside each training fold.
Context and aliases
Level: Intermediate. Stages: Theory · Evaluation · Research.
Tags: ML · DL · SLM · LLM.
Aliases: CV.
Related concepts
Concepts linking here
Technology connections
- AutoGluon — AutoML toolkit covering tabular and other supported prediction tasks.
- CatBoost — Gradient boosting with dedicated categorical-feature handling.
- FLAML — Resource-aware AutoML and optimization library.
- H2O-3 — Distributed platform for classical ML and AutoML.
- LightGBM — Histogram-based gradient-boosted tree framework.
- River — Online machine-learning library for streaming observations.
- scikit-learn — Consistent estimators, transforms and evaluation utilities for classical ML.
- statsmodels — Statistical estimation, tests and model diagnostics in Python.
- XGBoost — Optimized gradient-boosted decision-tree library.
Original references
- scikit-learn: cross-validation ↗ · Reference link
- Mathematics for Machine Learning ↗ · Reference link
- scikit-learn: evaluation metrics ↗ · Reference link
- Original reference URL ↗