Unverified50% confidenceFactExact time
The eigenvalue decay rate directly determines the smoothness of the RKHS and the generalization error bound: the faster the decay, the "smaller" the function space, and the more the model tends to learn smooth functions.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe choice of rank r is a trade-off between accuracy and efficiency: the smaller the r, the higher the compression ratio but the larger the approximation error.76% similarUnverifiedThe magnitude of the spectral truncation error is jointly determined by the Sobolev smoothness of the function and the truncation order; the smoother the function, the faster the high-frequency decay and the smaller the truncation error.73% similarUnverifiedUnder a local quadratic model, a larger batch means fewer but longer update steps, with each step incurring a greater loss on curvature, resulting in a critical batch size that depends on the learning rate, beyond which sample efficiency declines.72% similarUnverified梯度下降的收敛条件与学习率和损失函数的Lipschitz常数的关系有关72% similarUnverified低精度引入的数值扰动会在RL的多轮迭代中通过策略梯度的乘积形式被放大，可能导致训练崩溃或模型性能退化72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102477API
curl https://kongchang.com/api/v1/knowledge/claims/1102477MCP
get_claim(id=1102477)