Glossary · Term

progressive growth

← all terms

Definition

Starting with a small AI system that works, then gradually adding more parts that train on top of it.

A training schedule that scales multi-agent topologies (or networks) by initializing new components with zero contribution and gradually training them against an already-converged smaller system.

Mentioned in 1 episode

  1. 060
    When Splitting One Model Across Three Agents Doubles Its Accuracy