English(EN) Noise-shaped Sampling and Annealing for Scalable On-the-edge Training of Binary and Ternary AI Models

新的训练方法可实现二元和三元AI模型的高效设备端训练

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-19 04:00

研究人员开发了一种名为“$\Sigma\Delta$-Sampler”的新训练方法，该方法利用Ising求解器更有效地训练二元和三元AI模型。该方法将随机采样和退火步骤嵌入噪声整形循环中，有效地将噪声推离关键的自适应频带。该方法已在QUBO、CIFAR-10、ImageNet-1k和大型语言模型等各种基准测试中得到验证，在准确性方面取得了显著的改进，并大大减少了内存占用和训练时间。 AI

影响减少了二元和三元模型的内存占用并加快了训练速度，从而实现了设备端训练。

排序理由详细介绍AI模型新训练方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 9 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍AI模型新训练方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Zihao Chen, Zhili Xiao, Rui-Jie Zhu, Yipeng Wang, Jason Eshraghian, Shantanu Chakrabartty · 2026-10-19 04:00

面向二值和三值AI模型边缘可扩展训练的噪声整形采样与退火

arXiv:2610.22621v1 Announce Type: new Abstract: The training loss of binary and ternary neural networks, expanded as a multilinear polynomial over the discrete weights, is structurally equivalent to the energy of a hierarchical high-order Ising model. We exploit this equivalence …

本文如何被排名

报道来源 [1]

面向二值和三值AI模型边缘可扩展训练的噪声整形采样与退火

相关实体

相关话题