This improves the best known exact gradient methods by a factor of p nnz(A)/n and is faster than fully stochastic gradient methods in the accurate and/or sparse regime apple p n/nnz(A).

Optimal transportation, or computing the Wasserstein or "earth mover's" distance between two n-dimensional distributions, is a fundamental primitive which arises in many learning and statistical settings.

This improves the best known exact gradient methods by a factor of p nnz(A)/n and is faster than fully stochastic gradient methods in the accurate and/or sparse regime apple p n/nnz(A).

Optimal transportation, or computing the Wasserstein or "earth mover's" distance between two n-dimensional distributions, is a fundamental primitive which arises in many learning and statistical settings.

How accurately can one recover the "histogram" (i.e.

Neural Information Processing Systems http://nips.cc/