Unverified50% confidenceFactExact time
In the deterministic setting without Dropout, the optimal approximation rate for Sobolev space approximation is benchmarked by a parameter complexity of ε^{-d/n}, as studied by Barron, DeVore, and others.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen d is much greater than n, the minimum-norm solution can be selected via the Moore-Penrose pseudoinverse X^T(XX^T)⁻¹y, and the stability of the solution is improved.66% similarUnverifiedThe lower-bound argument comes from two perspectives: Sobolev capacity constraints and the output-layer cost for approximating a fixed affine function.66% 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64% similarUnverifiedε-prediction is prone to numerical instability at large embedding dimensions, because when α_bar_t approaches zero the scaling factor 1/sqrt(α_bar_t) tends to infinity, amplifying prediction errors.63% similarUnverified朴素贝叶斯中需要使用对数概率空间来规避连乘小概率值导致的下溢63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975782API
curl https://kongchang.com/api/v1/knowledge/claims/975782MCP
get_claim(id=975782)