English(EN) Decision-Aware Quadratic ReLU Replacement for HE-Friendly Inference

新的二次ReLU替代方案加速FHE神经网络推理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-22 04:00

研究人员开发了一种新方法，用于将神经网络中的ReLU激活函数替换为二次多项式，特别适用于全同态加密（FHE）。该方法旨在通过使用低次多项式来降低仅FHE推理的计算成本，同时保持校准数据集上的分类准确性。该方法将替换问题构建为线性分离问题，并使用凸包松弛将其扩展到误分类样本的情况，与现有方法相比实现了更快的推理速度。 AI

影响使得使用全同态加密的神经网络能够进行更高效的推理，有可能降低成本并增加采用率。

排序理由详细介绍新颖技术方法的学术论文。[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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍新颖技术方法的学术论文。[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: 139 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Rui Li, Wenyuan Wu, Weijie Miao · 2026-05-22 04:00

面向HE友好推理的决策感知二次ReLU替换

arXiv:2605.22237v1 Announce Type: cross Abstract: Fully homomorphic encryption (FHE) supports only additions and multiplications, so FHE-only neural-network inference typically replaces ReLU with polynomials fitted over empirical activation intervals. Such interval fitting often …

本文如何被排名

报道来源 [1]

面向HE友好推理的决策感知二次ReLU替换

相关实体

相关话题