Habibur Rahaman, Swarup Bhunia · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28872 · open-access PDF
훈련된 네트워크의 무게는 모델 정확성에 대한 동일한 민감성을 가지고 있지 않다: 가장 민감한 무게의 1 %는 훈련된 모델의 비트 플립 수용량, 코드가 덮어야 할 무게의 부분 및 각 무게에 필요한 비트의 비트에 대한 비트 플립 수용량을 결정합니다; 기존 계획은 배포 훈련 잎과 함께 작동합니다. 우리는 우리가 체계적으로 훈련 된 모델의 무게 민감성 분포를 조절하거나 변경할 수 있음을 보여줍니다.
Machine translation (Meta M2M100); the English original follows.
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. This distribution decides the bit-flip tolerance of a model, the fraction of weights a code must cover and the bits each weight needs; existing schemes work with the distribution training leaves. We show that we can systematically modulate or alter the weight sensitivity distribution of a trained model, thereby shifting weights from one sensitivity bin to another. The sensitivity of a stored weight is the product of its gradient
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28872, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange