arXiv · Statistics Machine Learning· Shivam Shrivastava·· 16 小时前AI 评分32
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
Below what training size do deep tabular generators stop beating trivial baselines? A preregistered benchmark on a size ladder of clinical and standard datasets
AI 导读
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。
来源：arXiv · Statistics Machine Learning · arxiv.org