regularization
/ˌrɛɡjʊləraɪˈzeɪʃən/
Definition
A mathematical technique applied during the training of statistical models to prevent overfitting by adding a penalty term that discourages overly complex solutions.
Etymology
Derived from the Latin word 'regula' meaning 'rule' or 'standard,' the term evolved into the verb 'regularize' to denote making something conform to a rule; the '-ation' suffix creates the noun form identifying the technical process of enforcing such constraints.
In the news
In this article, regularization was used within machine learning algorithms, specifically a LASSO model, to improve the reliability and predictive accuracy of antidepressant response models by penalizing unnecessary complexity in the data.
A precision medicine trial of bupropion and sertraline for major depressive disorder using a biomarker-guided sequential multiple-assignment design
Read the full article ↗Nature