Unverified50% confidenceFactExact time
Under the setting of a shared regression function and commutable power-law covariance spectra, there exists a region where the scaling law achieves the minimax-optimal exponent.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn a univariate Gaussian distribution, the mean μ controls the location and the variance σ² controls the degree of dispersion.69% similarUnverifiedThe fixed-point score matching framework has limitations: the score is inherently a local quantity, and when the modes of the target distribution are far apart, the method struggles to correctly weigh the relative weights of the modes.69% similarUnverifiedThe separation result generalizes to weighted fixed-count targets, as long as the weight ratios are bounded and the quota proportions are bounded away from 0 and 1, the separation holds even without permutation symmetry.68% similarUnverifiedUnbalanced optimal transport allows marginal constraints to be softly satisfied by introducing penalty terms such as KL divergence into the objective function, giving lower-confidence matches smaller weights.68% similarUnverifiedWhen the conjugate gradient method solves symmetric positive definite linear systems, the number of iterations required for convergence is closely related to the condition number of the matrix—the larger the condition number, the slower the convergence.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1068991API
curl https://kongchang.com/api/v1/knowledge/claims/1068991MCP
get_claim(id=1068991)