Timezone: »

COT-GAN: Generating Sequential Data via Causal Optimal Transport
Tianlin Xu · Li Kevin Wenliang · Michael Munn · Beatrice Acciaio

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #938

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.

Author Information

Tianlin Xu (London School of Economics and Political Science)
Li Kevin Wenliang (Gatsby Unit, UCL)
Michael Munn (Google)
Beatrice Acciaio (ETH Zurich)

More from the Same Authors