Glossary · Term

regularization

← all terms

Definition

Plain language

Any technique that keeps a model from clinging too hard to its training examples, so it stays flexible on new ones.

As stated in the literature

Methods that constrain model capacity or penalize complexity — weight penalties, dropout, early stopping, auxiliary losses — to improve generalization; also invoked loosely to explain incidental gains from auxiliary objectives.

Also called: regularize, regularizing, regularizer

Why it matters: It matters because these techniques are what keep a model general enough to perform well on data it hasn't seen.

For example, randomly switching off some of a network's connections during training keeps it from leaning too hard on any single pattern.

Heard on the show

“The authors frame it as a deliberate design choice, and it clearly works as a regularizer.”
Episode 115 — Teaching a Phone Agent to Reason Silently, And Keeping It Honest

Mentioned in 5 episodes

  1. 115
    Teaching a Phone Agent to Reason Silently, And Keeping It Honest
  2. 084
    Terminal Agents Get Free Supervision From The Tokens We've Been Throwing Away
  3. 041
    When the Iteration Teaches the Model to Skip the Iteration
  4. 025
    The Missing Gradient Term That Predicts Sycophancy in RLHF
  5. 010
    When Reward Climbs But Reasoning Goes Generic: Diagnosing Template Collapse in Agentic RL

Related concepts

Related terms