Unverified50% confidenceFactExact time
Johnson-Lindenstrauss引理指出在n维空间中可以找到指数级于n的近似正交向量集合
1
Sources
50%
Confidence
Long-term
Relevance
7/9/2026
First Seen
Sources
Block-Sparse Featurizers: Opening the Black Box of Vision Model Neural Geometry
hackernewshackernews7/7/2026
Related Claims
UnverifiedThe Johnson-Lindenstrauss lemma guarantees that for any ε∈(0,1), as long as the target dimension k≥O(log(n)/ε²), there exists a mapping from high dimensions to k dimensions that preserves all pairwise distances within a factor of (1±ε).72% similarUnverified在n维空间中一个临界点成为局部极小值的概率约为(1/2)^n，因为要求Hessian矩阵的所有n个特征值都为正69% similarUnverified龙曲线的豪斯多夫维度为 2，意味着在无穷迭代极限下能完全填充二维平面区域65% similarUnverified算子理论是泛函分析的核心分支，研究无穷维空间（如希尔伯特空间、巴拿赫空间）上的线性映射及其性质65% similarUnverified在n维空间中，一个临界点成为局部极小值的概率约为(1/2)^n，因此现代大型网络的几乎所有临界点都是鞍点而非局部极小值61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/318170API
curl https://kongchang.com/api/v1/knowledge/claims/318170MCP
get_claim(id=318170)