Optimal transport has gained increasing attention in recent years due to the modeling power and computational tractability. In this talk, I will first study the duality of optimal transport for discrete probability measures and extend to continuous probability measures. Then, I will talk about the optimization to solve optimal transport problems via the Sinkhorn methods. I will also study the statistical properties of optimal transport: the curse of dimensionality. I will present two ideas to beat the curse of dimensionality: projection and smoothing. Finally, I  will discuss two applications: Wasserstein GANs and distributionally robust optimization.