Hot eventLive
深度表格生成器在小规模训练下不优于简单基线:预注册基准
1 reports1 sources16 hr ago updated
Get the story
AI overview
一项预注册的规模阶梯基准研究在 8 个公开数据集上展开,训练样本规模覆盖 200 至 20,000 行,比较了 7 种生成器,包括 independent marginals、Gaussian copula 等方法。研究关注深度表格生成器在较小训练规模下是否仍能胜过简单基线,结果显示在多个小训练规模下深度生成器并不优于平凡基线。该研究以预注册方式设计,旨在减少事后选择偏差。目前公开信息仅给出数据集数量、规模区间与生成器数量,完整结果细节尚未披露。
Generated from reports · updated 16 hr ago
Timeline
Follow the coverage from different angles.
Oct 5, 2026
- arXiv · Statistics Machine Learning深度表格生成器在多小训练规模下会输给简单基线?一项预注册规模阶梯基准
一项预注册基准在 8 个公开数据集上以 200 至 20,000 行训练样本、7 种生成器(independent marginals、Gaussian copula。
Heat trend
Current heat 7·Comparable peak 10(Oct 5)·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.