Glossary · Term

phantom gradients

← all terms

Definition

A clever way of training fixed-point models that avoids running the full implicit-gradient computation.

An approximation technique for training implicit models that estimates gradients through the equilibrium without the full inverse-Jacobian solve, used in attractor-model reasoning experiments.

Mentioned in 1 episode

  1. 041
    When the Iteration Teaches the Model to Skip the Iteration