Unverified50% confidenceFactExact time
In standard training, gradient descent has a uniform convergence rate guarantee on smooth convex problems, independent of the specific data distribution.
1
Sources
50%
Confidence
Long-term
Relevance
11/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLinear probes perform well on the training distribution, but their performance often drops sharply when facing out-of-distribution (OOD) samples.80% similarUnverifiedModern training frameworks use mixed-precision training and gradient scaling (loss scaling) techniques to prevent small values from being swallowed by amplifying small gradients into the representable range.75% similarUnverifiedThe reason for using a correlation coefficient rather than simply comparing final loss values is that it can capture the dynamic consistency across the entire training run, which proves the numerical validity of the training process better than a single endpoint metric.74% similarUnverified计算最优（Compute-Optimal）并不等于集群最优（Cluster-Optimal），真正决定训练效率的因素远不止浮点运算次数73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1142249API
curl https://kongchang.com/api/v1/knowledge/claims/1142249MCP
get_claim(id=1142249)