Unverified50% confidenceFactExact time
Under the AM-GM optimal solution, the product of the minimum achievable variance and the budget equals (sqrt(a*tau^2) + sqrt(b*sigma^2))^2.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedUnder a fixed compute budget, the optimal number of repetitions is N* = sqrt(a * sigma^2 / (b * tau^2)), where sigma^2 is the per-question variance, tau^2 is the per-repetition (resampling) variance, and a and b are cost coefficients.76% similarUnverifiedFor the squared exponential kernel, γ_T = O((log T)^(d+1)), growing extremely slowly; for the Matérn-ν kernel, γ_T = Θ(T^(d/(2ν+d))), growing polynomially with T.65% similarUnverifiedUnder the assumption of a Gaussian output distribution, minimizing negative log-likelihood (NLL) and minimizing mean squared error (MSE) are mathematically completely equivalent.63% similarUnverifiedOn a well-conditioned zero-predictor family, the optimal B-bit compression yields a mean single-step update error on the order of d^{-1}·2^{-2B/s_d}, where s_d=d(d+1)/2.63% similarUnverifiedThe least squares method solves for regression coefficients by minimizing the residual sum of squares (RSS), where residuals refer to the difference between actual values and predicted values63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1014438API
curl https://kongchang.com/api/v1/knowledge/claims/1014438MCP
get_claim(id=1014438)