Unverified50% confidenceFactExact time
The Wasserstein distance is a metric defined on the space of probability distributions that measures the minimum cost required to transport one distribution into another; the p-Wasserstein distance is defined as W_p(μ,ν) = inf_{γ∈Γ(μ,ν)} (E_{(x,y)~γ}[||x-y||^p])^{1/p}.
1
Sources
50%
Confidence
Long-term
Relevance
11/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWasserstein距离是一个真正的度量，满足对称性和三角不等式，而KL散度不对称且在分布支撑不重叠时为无穷大69% similarUnverified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% similarUnverifiedSquared Hellinger distance is defined as H^2(p,q) = (1/2)∫(√p - √q)^2 dμ; it is symmetric and does not require absolute continuity, takes values between 0 and 1, and satisfies the equivalence relation with total variation distance that total variation distance does not exceed √2 H.65% similarUnverifiedThe Marčenko–Pastur law states that the upper bound of the support interval for the eigenvalue distribution of a purely random matrix is λ_max = σ²(1+√q)², where q = N/T.61% similarUnverifieds维Hausdorff测度定义为H^s(S) = lim_{δ→0} inf{Σ|U_i|^s}，Hausdorff维数定义为dim_H(S) = inf{s ≥ 0 : H^s(S) = 0}60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125682API
curl https://kongchang.com/api/v1/knowledge/claims/1125682MCP
get_claim(id=1125682)