神经科学约束下的Johnson-Lindenstrauss变换浅析
Simple Analysis of Johnson-Lindenstrauss Transform under Neuroscience Constraints
摘要:
本文重新分析了著名的约翰逊-林登施特劳斯引理的一个版本,其中矩阵受到神经科学应用中自然出现的约束:a)稀疏性和b)符号一致性。这种特殊的变体首先由Allen-Zhu,Gelashvili,Micali,Saught研究,最近由Jagadeesan(RANDOM'19)研究。这项工作的贡献是一个新的证明,与以前的作品相比,a)使用现代概率工具包,特别是亚高斯和亚伽马估计的基础知识b)是独立的,不依赖于微妙的第三方结果c)提供明确的常数。我们证明的核心是汉森-赖特引理(关于二次型的集中)的一个新变体。对亚高斯随机变量也有独立的兴趣。
英文摘要:
The paper re-analyzes a version of the celebrated Johnson-Lindenstrauss Lemma, in which matrices are subjected to constraints that naturally emerge from neuroscience applications: a) sparsity and b) sign-consistency. This particular variant was studied first by Allen-Zhu, Gelashvili, Micali, Shavit and more recently by Jagadeesan (RANDOM'19). The contribution of this work is a novel proof, which in contrast to previous works a) uses the modern probability toolkit, particularly basics of sub-gaussian and sub-gamma estimates b) is self-contained, with no dependencies on subtle third-party results c) offers explicit constants. At the heart of our proof is a novel variant of Hanson-Wright Lemma (on concentration of quadratic forms). Of independent interest are also auxiliary facts on sub-gaussian random variables.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。