Skip to content

Constrained Training Manifolds

Stabilize large-model training by restricting weight updates to curated manifolds that align with desired behaviors and safety envelopes.

advanced4 / 9

Stability gains and empirical observations

  • Training curves show reduced variance when attention weights are kept on orthogonal manifolds, leading to faster convergence.
  • Constraining intermediate representations can mitigate catastrophic forgetting during continual learning, since updates avoid directions that erase prior knowledge.
  • Safety-focused manifolds can cap amplification of risky behaviors by removing gradient directions associated with flagged patterns.
Section 4 of 9
Next →