Unverified50% confidenceFactExact time
Under the polynomial spectral decay (exponent α>1) and leverage compatibility assumptions, the squared L2 approximation rate of a two-layer network with width m and trainable proportion P is O((κ_P log(m/δ)/m)^α), where κ_P = (P/κ_1^* + (1-P)/κ_0^*)^{-1}.
1
Sources
50%
Confidence
Long-term
Relevance
10/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe paper proves that there exist networks of constant depth and size Õ_{n,d}(p^{-9}ε^{-max{d/n,2}}log(1/δ)) that satisfy the probabilistic uniform approximation requirement with probability at least 1-δ.70% similarUnverifiedThe Stein identity states that for a function φ that decays sufficiently fast on the boundary, when the probability density p(x) is sufficiently smooth on R^d, E_p[∇_x log p(x)·φ(x) + ∇_x·φ(x)] = 0.70% similarUnverifiedThe paper proves that when the true mixture measure satisfies the sub-Gaussian assumption, the unconstrained NPMLE achieves the minimax optimal rate log(n)/n under squared Hellinger distance.68% similarUnverifiedFor 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).68% similarUnverifiedWhen the reward density is uniformly bounded away from zero, the paper establishes a root-n high-probability bound that holds simultaneously for all resolutions m and all Wasserstein orders p (1 ≤ p ≤ ∞), with the estimation error converging at the parametric rate n^{-1/2}.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088316API
curl https://kongchang.com/api/v1/knowledge/claims/1088316MCP
get_claim(id=1088316)