One-Step Curvature Probes Miss the Fitting Operator: Retained Capacity and Terminal Null-Space Correction for Continual Learning
arXiv:2610.03952v1 Announce Type: new Abstract: A one-step curvature probe evaluates an initial direction, whereas continual learners are judged after reaching comparable new-task fit. In an overparameterized linearization, projected gradient descent converges to $\Delta_P=PJ^\top(JPJ^\top)^{-1}r$,…
Read the full story at arXiv cs.LG ↗