Unverified50% confidenceFactExact time
For learning tasks operating on an intrinsic d*-dimensional submanifold, the paper proves that the optimal partition scaling can achieve the minimax nonparametric rate O(n^{-1/(d*+2)}√ln n).
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe Fast Fourier Transform reduces the computational complexity of the DFT from the naive O(N²) to O(N log N).70% similarUnverifiedRegardless of which regime applies, estimators based on compression complexity stably maintain a convergence rate of O(1/√N).70% similarUnverifiedThe paper proves that the eigenpair convergence rate of a manifold-agnostic graph Laplacian estimator to the tensorized Laplace-Beltrami operator is n^{-1/(2.5d-1)} (ignoring logarithmic factors).69% similarUnverified直接在SO(3)上做卷积的朴素复杂度为O(B^6)，通过快速球面傅里叶变换（基于Driscoll-Healy或McEwen-Wiaux采样定理）可降低至O(B^5)甚至更低68% similarUnverifiedThe main result of the paper is that Q-Learning with zero initialization and constant step size can, with high probability, reduce the sup-norm error to within ε using Õ(H^4/(μ_min·ε^2)+h_star) state transitions (for 0<ε≤1).67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1046145API
curl https://kongchang.com/api/v1/knowledge/claims/1046145MCP
get_claim(id=1046145)