Unverified50% confidenceBenchmarkExact time
For log-concave distributions, the elliptic schedule requires only Õ(√d polylog(κ, 1/ε)) score evaluations to achieve a 2-Wasserstein error of ε.
1
Sources
50%
Confidence
Long-term
Relevance
11/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe paper proves that the learned generative distribution satisfies a finite-sample error bound in Wasserstein-p distance: W_p ≲ n^(-1/d) + n^(-1/(2p))(log(1/ξ))^(1/(2p)).73% similarUnverifiedThe relationship between the standard error of Monte Carlo estimation and the number of simulations N is that the standard error is proportional to 1/√N.70% similarUnverifiedUnder the assumption that the true mapping is uniformly random, the paper proves a lower bound on the error rate of E ≥ (M/N)δ*(B/M) + (1-M/N)(1-1/K).67% similarUnverifiedThe theoretical analysis gives upper bounds on the squared ℓ2 parameter estimation error: Õ(s*/n + s*^2/(n^2ε^2)) for Sample-DP and Õ(s*/n + s*/(nε^2)) for Label-DP (based on randomized response), where n is the amount of training data and ε is the privacy budget.66% similarUnverifiedIn i.i.d. sampling, the statistical error for n samples typically decays at the rate of 1/√n.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1175087API
curl https://kongchang.com/api/v1/knowledge/claims/1175087MCP
get_claim(id=1175087)