We leverage these advantages to derive a new algorithm Factor Relaxation with Latent Coupling (FRLC), which uses coordinate mirror descent to compute the LC factorization.

Given a source and a target probability measure, the Monge problem studies efficient ways to map the former onto the latter. This efficiency is quantified by defining a cost function between source and target data.

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

We introduce in this paper a novel strategy for efficiently approximating the Sinkhorn distance between twodiscrete measures.

Compared computation LA-SWtoGA-SWandNA-SW, the slightly; memory usingsliced computational LA-SWis itcoststhe Section 3A-SW.

Graph According graphs, T =[ Tij indicates Figure Graph Besides Recall 12]: for connecting sub-graph 21,47,34 graph K isolated, bycalculating dgw(G, Gdc), whereGdc = G(Vdc,diag whose Figure indicates 2.2 Gr Multi-graph Distinct focus byintroducing Based frame propose acceleration 3.1 Inspired 48,49...

Theworddistributions of topics, their optimal transports to the word distributions of documents, and the embeddings of words are learned in a unified framework. When learning thetopic model, weleverage adistilled underlying distance matrix toupdate the topic distributions and smoothly calculate the corresponding optimal transports.

These results give the first characterization of the large-sample behavior of entropic OT for unbounded probability measures in arbitrary dimension.

Theoretically, the focus is on fittingalargeclassofproblems intoasingleMinMax frameworkandgeneralizing regularization techniques knownfrom classical optimal transport.