Rethinking the Rank Threshold for LoRA Fine-Tuning

arXiv:2605.03724v1 Announce Type: cross Abstract: A recent landscape analysis of LoRA fine-tuning in the neural tangent kernel regime establishes a sufficient condition $r(r+1)/2 > KN$ on the LoRA rank $r$ for the absence of spurious local minima under squared-error loss, prescribing $r \geq 12$ on...