Unverified50% confidenceFactExact time
For products of scale families (including Gaussian covariance parameters, Gamma rate parameters, etc.), R grows unboundedly as Θ(√log d) with dimension d.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe paper defines the inefficiency ratio R as the Fisher length of the mixture geodesic divided by the Fisher–Rao distance, where R is always greater than or equal to 1.67% similarUnverifiedIn nonparametric density estimation, the number of samples required to achieve ε accuracy grows at a rate of ε^(-D) with the ambient dimension D.65% similarUnverifiedLLM每次调用可建模为伯努利试验，N次调用通过次数服从二项分布B(N, p)，通过率95%置信区间约为p̂ ± 1.96×√(p̂(1-p̂)/N)64% similarUnverifiedTaking D=4096 and r=8 as an example, the number of LoRA parameters is only 0.39% of the original, with a 250-fold reduction in computation.63% similarUnverifiedWhen two unit vectors are randomly sampled in d-dimensional space, their inner product has an expected value of 0 and a standard deviation of approximately 1/√d; when d=1024, the standard deviation is approximately 0.031.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/983529API
curl https://kongchang.com/api/v1/knowledge/claims/983529MCP
get_claim(id=983529)