Unverified50% confidenceFactExact time
The 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.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe universal approximation theorem for neural networks states that a sufficiently wide or sufficiently deep network can approximate any continuous function, but does not answer the question of what network size is required to achieve a specific accuracy.71% similarUnverifiedThe upper-bound network size has a ninth-power dependence of p^{-9} on the Dropout retention probability p, meaning that the lower the retention probability, the more sharply the required network size grows.66% similarUnverifiedBarnes-Hut 优化通过空间八叉树将远距离节点群近似为单一质心，将计算复杂度从 O(N²) 降低到 O(N log N)65% similarUnverifiedSoftmax函数将神经网络logits压缩为概率分布，但其输出值在大规模模型中系统性偏离真实贝叶斯后验概率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% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975783API
curl https://kongchang.com/api/v1/knowledge/claims/975783MCP
get_claim(id=975783)