Unverified50% confidenceFactExact time
The supremum norm is defined as the maximum deviation of a function over its entire domain, is stronger than L2 or W2, and requires all points to be approximated simultaneously.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe limiting log marginal likelihood derived under the HTMP assumption is a convex function with respect to the heavy-tail degree parameter.63% similarUnverifiedThe 2-Wasserstein distance is more sensitive to the geometric shape of the support sets of distributions than KL divergence, and can yield meaningful finite distance values even when the support sets of two distributions do not overlap.62% similarUnverifiedIn a univariate Gaussian distribution, the mean μ controls the location and the variance σ² controls the degree of dispersion.61% similarUnverifiedEXL2 支持混合精度量化，按重要性为不同权重分配位宽，在相同平均位宽下往往比同等 GGUF 模型在精度敏感任务上表现更优61% similarUnverified正交变换保持向量的L2范数和向量间夹角不变，正交矩阵的条件数恒为161% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1022965API
curl https://kongchang.com/api/v1/knowledge/claims/1022965MCP
get_claim(id=1022965)