LLQR+SAM pairs a slow learned geometry preconditioner with fast SAM perturbations to amplify escape from locally sharp 'potholes' while stabilizing flat basins, producing consistent gains over SAM and LLQR alone.
5th International Conference on Learning Representations
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
citing papers explorer
-
Navigating Potholes with Geometry-Aware Sharpness Minimization
LLQR+SAM pairs a slow learned geometry preconditioner with fast SAM perturbations to amplify escape from locally sharp 'potholes' while stabilizing flat basins, producing consistent gains over SAM and LLQR alone.
- Symmetrization of Loss Functions for Robust Training of Neural Networks in the Presence of Noisy Labels
- From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing