Unverified
2026
Fisher-Width-Balanced Sparse Fine-Tuning
Select the coordinates of a sparse adapter or sparse fine-tuning mask using both Fisher width and inverse-Fisher width. The mask should avoid parameter subsets that are cheap in the Fisher geometry but extremely large in the inverse-Fisher geometry, or vice versa, thereby controlling both prediction sensitivity and estimator-like uncertainty.
Paper: Fisher Widths: Local Learning Geometry and Anisotropic Recovery
arXiv:2607.20578