Generative Modeling for Tabular Data via Penalized Optimal Transport Network

arXiv:2402.10456v1 Announce Type: cross
Abstract: The task of precisely learning the probability distribution of rows within tabular data and producing authentic synthetic samples is both crucial and non-trivial. Wasserstein generative adversarial network (WGAN) marks a notable improvement in generative modeling, addressing the challenges faced by its predecessor, generative adversarial network. However, due to the mixed data types and multimodalities prevalent in tabular data, the delicate equilibrium between the generator and discriminator, as well as the inherent instability of Wasserstein distance …

abstract adversarial arxiv authentic challenges cs.lg data distribution generative generative adversarial network generative modeling improvement marks modeling network probability samples stat.ap stat.me stat.ml synthetic tabular tabular data transport type via wgan