Unverified50% confidenceFactExact time
The authors extend the lower bound to approximation of targets in W^{n,r} space measured by L^s error, and distinguish the differences between this extension and the upper bound in the W^{n,∞} case.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
Unverified一维Wasserstein-1距离等于两个累积分布函数之间面积的积分 W₁ = ∫|F_A(x) - F_B(x)|dx66% similarUnverifiedThe 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).64% similarUnverified感受野大小可通过递归公式计算：RF_L = RF_{L-1} + (k_L - 1) × ∏_{i=1}^{L-1} s_i62% similarUnverifiedThe mathematical operation for ablating the refusal direction is a' = a - (a · r̂) r̂, which orthogonally projects the activation vector onto a hyperplane orthogonal to the refusal direction.61% similarUnverified雅可比矩阵描述关节空间速度到笛卡尔空间速度的映射，末端位置误差δx = J·δθ61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975790API
curl https://kongchang.com/api/v1/knowledge/claims/975790MCP
get_claim(id=975790)