Unverified50% confidenceFactExact time
The paper proves that, under appropriate network depth and width configurations, the convergence rate of dense ReLU networks can overcome the curse of dimensionality, achieving polynomial-level sample complexity.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe conclusion of overcoming the curse of dimensionality relies on the conditional distribution having a certain smoothness structure (such as Hölder smoothness) and on a refined characterization of the relationship between network depth, width, and the smoothness of the target function.78% similarUnverifiedThe 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.77% similarUnverified反向传播机制要求整个计算图必须是可微分的，且在极深网络中存在梯度消失/爆炸问题74% similarUnverifiedThe 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.72% similarUnverifiedThe original LISCO adopts a dense monolithic network architecture whose network size grows linearly with the prediction horizon, making it difficult to scale to long-horizon, large-scale problems.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023496API
curl https://kongchang.com/api/v1/knowledge/claims/1023496MCP
get_claim(id=1023496)