论文标题
cot-gan：通过因果最佳传输生成顺序数据
COT-GAN: Generating Sequential Data via Causal Optimal Transport
论文作者
论文摘要
我们介绍了一种对抗性算法COT-GAN，用于训练用于生成顺序数据的优化的隐式生成模型。该算法的损失函数是使用因果最佳运输（COT）的想法制定的，该想法结合了经典的最佳传输方法与其他时间因果关系约束。值得注意的是，我们发现这种因果关系提供了一个自然框架，可以参数化歧视者学到的成本函数，作为一个健壮的（最坏情况）距离，并且是学习时间相关数据分布的理想机制。在Genevay等人（2018）之后，我们还包括一个熵惩罚术语，该项允许在计算最佳运输成本时使用Sinkhorn算法。我们的实验在生成低维和高维时间序列数据时显示出COT-GAN的有效性和稳定性。该算法的成功还依赖于Sinkhorn Divergence的新的，改进的版本，该版本表现出较少的学习偏见。
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.
