Unverified60% confidenceFactExact time
Due to its asymmetry, KL divergence does not satisfy the triangle inequality of a distance metric and is strictly referred to as a divergence rather than a distance.
2
Sources
60%
Confidence
Long-term
Relevance
8/2/2026
First Seen
Sources
From Entropy to Cross-Entropy: An Information-Theoretic Derivation of the Logistic Regression Loss Function
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76% similarUnverifiedK-means assumes clusters are convex and isotropic, performs poorly on non-spherical distributions, and is extremely sensitive to outliers.66% similarUnverifiedThe sharp marginal lower bound is discontinuous in the answer space, and there exists no label-free lower bound that is continuous under the Wasserstein distance and can approach this sharp lower bound within a constant factor.60% similarUnverifiedWhen the convex function φ in the Bregman divergence is taken as the squared norm, it yields the squared Euclidean distance; when taken as the negative entropy, it yields the KL divergence; and when taken as the negative logarithm, it corresponds to the Itakura-Saito divergence.60% 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60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/679899API
curl https://kongchang.com/api/v1/knowledge/claims/679899MCP
get_claim(id=679899)