Newest papers

LEAN: Loss-Engineered Modulation of the Model Weight-Sensitivity Distribution for Efficient, Error-Tolerant Neural Networks

Habibur Rahaman, Swarup Bhunia · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28872 · cited by 0 works (OpenAlex) · open-access PDF

Arabic

لا توجد تقييمات متساوية من شبكة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترجمة الترج

Machine translation (Meta M2M100); the English original follows.

Abstract

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 and the step a flip takes in the storage format, and LEAN adds a composite regularizer on both factors, a range term that bounds the flip step and a tail term that lowers the gradient of the most sensitive weights, with one coefficient λ setting how far the distribution moves. Ten epochs with the term, as a fine-tune or as the last epochs of training, shrink the sensitive tail 5 to 13 times on nine vision models (ResNet-18, ResNet-50, VGG-16 on CIFAR-10, CIFAR-100, ImageNet) within 0.5 points of accuracy; real flips confirm that the reshaped weights do less damage, a plain gradient-norm penalty does not reproduce the effect, and a preliminary extension to three small language models shows the same tail shaping. With a BCH code over 1% of the weights the model then survives 300 progressive bit-search flips in every training seed and 500 in two of three, where three of four published defenses with the same code fail by 300 and WCAT falls to 75% at 500. The reshaped distribution also cuts the parity for a fixed guarantee 3.7 times and makes a sensitivity-ordered 8/6/4/3-bit format affordable, which stores ImageNet ResNet-50 at a 3.29-bit weight payload, 2.4 times smaller than INT8, above the accuracy of LSQ at 3 bits.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Weight distribution, Sensitivity (control systems), Bin, Distribution (mathematics), Algorithm, Mathematics

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: 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.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange