PulseAugur
中
实时 10:17:08
English(EN) Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven

随机哈达玛变换被证明对AI量化有效

研究人员已从数学上证明,在各种AI应用中使用随机哈达玛变换(RHTs)作为统一随机旋转的高效替代方法是有效的。研究表明,组合两个RHTs可以确保单个坐标分布近似高斯分布,在DRIVE和QUIC-FL等方案中可媲美URRs的性能。对于向量量化,需要三个RHTs才能实现衰减的坐标协方差,从而确保与URRs相当的性能。该研究还引入了一种运行时检查,以动态调整使用的RHTs数量,从而优化实际非对抗性输入的性能。 AI

影响 为高效的AI模型压缩和加速技术提供了理论支持,有望提高推理速度并减少内存使用。

排序理由 该集群包含一篇学术论文,详细介绍了用于AI基础设施的技术的理论进展和证明。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

随机哈达玛变换被证明对AI量化有效

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
Research
该集群包含一篇学术论文,详细介绍了用于AI基础设施的技术的理论进展和证明。
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
145 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [3]

  1. arXiv cs.LG TIER_1 English(EN) · Boris Prokhorov ·

    基于随机哈达玛变换的可证明量化

    Vector quantization via random projection followed by scalar quantization is a fundamental primitive in machine learning, with applications ranging from similarity search to federated learning and KV cache compression. While dense random rotations yield clean theoretical guarante…

  2. arXiv cs.LG TIER_1 English(EN) · Ran Ben-Basat, William Kuszmaul, Michael Mitzenmacher, Amit Portnoy, Shay Vargaftik ·

    使用随机Hadamard变换进行量化:高效启发式方法现已获证明

    arXiv:2605.06014v1 Announce Type: new Abstract: Uniform random rotations (URRs) are a common preprocessing step in modern quantization approaches used for gradient compression, inference acceleration, KV-cache compression, model weight quantization, and approximate nearest-neighb…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    使用随机Hadamard变换进行量化:高效启发式方法现已获证明

    Uniform random rotations (URRs) are a common preprocessing step in modern quantization approaches used for gradient compression, inference acceleration, KV-cache compression, model weight quantization, and approximate nearest-neighbor search in vector databases. In practice, URRs…