Unverified50% confidenceFactExact time
The theoretical foundations of functional gradient descent come from Reproducing Kernel Hilbert Spaces (RKHS) and variational methods in function space.
1
Sources
50%
Confidence
Long-term
Relevance
9/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Fourier basis of value functions defined on binary vector spaces is the Walsh-Hadamard transform basis, and sparsity means that the main structure of the function can be recovered with far fewer than 2^n samples.63% similarUnverified拉格朗日对偶通过引入拉格朗日乘子将约束吸收进目标函数，再利用 KKT 条件转化为对偶问题，引出支持向量和核技巧的理论基础61% similarUnverified双重下降现象的理论解释包括隐式正则化假说、插值阈值理论和神经正切核框架，但尚未形成统一理论框架60% similarUnverifiedCybenko的原始证明利用了Hahn-Banach定理来证明神经网络所张成的函数子空间在连续函数空间C(K)中稠密58% similarUnverifiedGPTQ is a layer-wise quantization method based on approximate second-order information, proposed by Frantar et al. in 2022, which minimizes quantization reconstruction error through the approximate inverse of the Hessian matrix.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/956485API
curl https://kongchang.com/api/v1/knowledge/claims/956485MCP
get_claim(id=956485)