Lean3 min read
LEAN: Loss-Engineered Modulation of the Model Weight-Sensitivity Distribution for Efficient, Error-Tolerant Neural Networks
The weights of a trained network do not have uniform sensitivity to model accuracy: the 1% most sensitive weights carry about a fifth of the damage a bit flip can do.
By Habibur Rahaman, Swarup BhuniaarXiv cs.LG
Read the full story
Originally published by arXiv cs.LG on Oct 22, 2026.
Comments
Sign in to join the discussion.