Unverified50% confidenceFactExact time
The finite-sample bound compares the network with its Gaussian limit on a fixed finite sample set, using the quadratic Wasserstein distance W2, with a convergence rate of m^{-1/2} and explicit constants, but the constants grow with the number of samples, and the bound becomes uninformative as the sample set is progressively refined.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedStochastic gradient descent divides data into mini-batches of size m to approximate the gradient, enabling n/m updates per epoch instead of one.69% similarUnverifiedWasserstein distance bypasses the label permutation problem by representing clustering partitions as probability measures and solving an optimal transport problem, measuring the minimum total cost required to transport one partition into another.67% similarUnverified在有限观测窗口内捕获足够样本量所需的时间与系统规模成严格的反比关系67% similarUnverifiedWhen a model encounters out-of-distribution inputs, prediction entropy increases, the softmax output tends toward a uniform distribution, and the range of candidate tokens permitted by nucleus sampling expands, giving long-tail anomalous tokens a chance of being sampled.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1022956API
curl https://kongchang.com/api/v1/knowledge/claims/1022956MCP
get_claim(id=1022956)