Review for NeurIPS paper: Sinkhorn Barycenter via Functional Gradient Descent

This paper proposes a new method to compute the (Sinkhorn) of barycenter of several probability measures. In practice, the method scales well computationally and in high-dimension and the authors provide some theoretical support. Reviewers agree that this paper is strong with only minor weaknesses (such as the exponential dependency in 1/gamma; which in related work is often suboptimal). I thus recommend accept (poster).