Hot eventLive
FID样本最优估计论文发布
1 reports1 sources3 hr ago updated
Get the story
AI overview
2026年10月7日,一篇题为“FID 的样本最优估计”的论文在 arXiv 的 Statistics Machine Learning 栏目发布(一手来源)。该论文研究高斯分布间 FID 估计的样本复杂度,给出经验 plug-in 估计器的偏差界为 Θ(d²/n)、方差界为 Θ(d/n + d²/n²),并证明其样本复杂度下界为 ≳ d²。目前公开信息仅涉及该论文的理论结果,未见后续实验验证或同行评议进展报道。
Generated from reports · updated 3 hr ago
LatestOct 7
论文给出高斯分布间FID经验plug-in估计器的偏差、方差界及≳d²的样本复杂度下界。Timeline
Follow the coverage from different angles.
Oct 7, 2026
- arXiv · Statistics Machine LearningFID 的样本最优估计
论文研究高斯分布间 FID 估计的样本复杂度,给出经验 plug-in 估计器 Θ(d²/n) 偏差与 Θ(d/n + d²/n²) 方差界,证明其样本复杂度下界为 ≳ d²。
Heat trend
Current heat 9·Comparable peak 10(Oct 7)·Comparable change over 24 hours –
The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.