Balanced Marginal and Joint Distributional Learning for Tabular Data Synthesis via Mixture Cramer–Wold Distance

In recent times, slicing methods have yielded a successful outcome in generative models for image, sound, and text data, primarily focusing on joint distributional learning. However, we have identified a critical limitation of the slicing approach for tabular data: it struggles to capture marginal d...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Seunghwan An, Sungchul Hong, Jong-June Jeon
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	MDPI AG 2026-03-01
Цуврал:	Applied Sciences
Нөхцлүүд:	synthetic tabular data distributional learning mixture Cramer–Wold distance
Онлайн хандалт:	https://www.mdpi.com/2076-3417/16/6/2928
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!