COT-GAN: Generating Sequential Data via Causal Optimal Transport

TL;DR

COT-GAN introduces a novel adversarial training method for sequential data using causal optimal transport, effectively learning time-dependent distributions with improved stability and less bias.

Contribution

The paper proposes COT-GAN, a new generative model leveraging causal optimal transport with an enhanced Sinkhorn divergence for stable, time-aware sequence generation.

Findings

Effective generation of low- and high-dimensional time series data

Stable training with improved Sinkhorn divergence

Robust learning of time-dependent distributions

Abstract

We introduce COT-GAN, an adversarial algorithm to train implicit generative models optimized for producing sequential data. The loss function of this algorithm is formulated using ideas from Causal Optimal Transport (COT), which combines classic optimal transport methods with an additional temporal causality constraint. Remarkably, we find that this causality condition provides a natural framework to parameterize the cost function that is learned by the discriminator as a robust (worst-case) distance, and an ideal mechanism for learning time dependent data distributions. Following Genevay et al.\ (2018), we also include an entropic penalization term which allows for the use of the Sinkhorn algorithm when computing the optimal transport cost. Our experiments show effectiveness and stability of COT-GAN when generating both low- and high-dimensional time series data. The success of the algorithm also relies on a new, improved version of the Sinkhorn divergence which demonstrates less bias in learning.