Massively scalable Sinkhorn distances via the Nyström method

12/12/2018
by   Jason Altschuler, et al.
4

The Sinkhorn distance, a variant of the Wasserstein distance with entropic regularization, is an increasingly popular tool in machine learning and statistical inference. We give a simple, practical, parallelizable algorithm NYS-SINK, based on Nyström approximation, for computing Sinkhorn distances on a massive scale. As we show in numerical experiments, our algorithm easily computes Sinkhorn distances on data sets hundreds of times larger than can be handled by state-of-the-art approaches. We also give provable guarantees establishing that the running time and memory requirements of our algorithm adapt to the intrinsic dimension of the underlying data.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset