Conference
Open access
Sep 2026
Generating High-Diversity Synthetic Tabular Data via Less-Constrained Prior
This work empirically demonstrate that the model, which relies on a single prior distribution, significantly improves the quality of the synthetic data, especially in terms of diversity.
Sanghun Park, Jaesung Lim, Jong-June Jeon et al.
· Proceedings of the Thirty-Fi... · 0 citations