%0 Journal Article %1 nielsen2018chain %A Nielsen, Frank %A Sun, Ke %D 2018 %K optimal-transport %T On The Chain Rule Optimal Transport Distance %U http://arxiv.org/abs/1812.08113 %X We define a novel class of distances between statistical multivariate distributions by solving an optimal transportation problem on their marginal densities with respect to a ground distance defined on their conditional densities. By using the chain rule factorization of probabilities, we show how to perform optimal transport on a ground space being an information-geometric manifold of conditional probabilities. We prove that this new distance is a metric whenever the chosen ground distance is a metric. Our distance generalizes both the Wasserstein distances between point sets and a recently introduced metric distance between statistical mixtures. As a first application of this Chain Rule Optimal Transport (CROT) distance, we show that the ground distance between statistical mixtures is upper bounded by this optimal transport distance and its fast relaxed Sinkhorn distance, whenever the ground distance is joint convex. We report on our experiments which quantify the tightness of the CROT distance for the total variation distance, the square root generalization of the Jensen-Shannon divergence, the Wasserstein $W_p$ metric and the Rényi divergence between mixtures.

@article{nielsen2018chain, abstract = {We define a novel class of distances between statistical multivariate distributions by solving an optimal transportation problem on their marginal densities with respect to a ground distance defined on their conditional densities. By using the chain rule factorization of probabilities, we show how to perform optimal transport on a ground space being an information-geometric manifold of conditional probabilities. We prove that this new distance is a metric whenever the chosen ground distance is a metric. Our distance generalizes both the Wasserstein distances between point sets and a recently introduced metric distance between statistical mixtures. As a first application of this Chain Rule Optimal Transport (CROT) distance, we show that the ground distance between statistical mixtures is upper bounded by this optimal transport distance and its fast relaxed Sinkhorn distance, whenever the ground distance is joint convex. We report on our experiments which quantify the tightness of the CROT distance for the total variation distance, the square root generalization of the Jensen-Shannon divergence, the Wasserstein $W_p$ metric and the R\'enyi divergence between mixtures.}, added-at = {2019-12-11T14:20:51.000+0100}, author = {Nielsen, Frank and Sun, Ke}, biburl = {https://www.bibsonomy.org/bibtex/2ef9011512b4baba8fea2615e2b24c28f/kirk86}, description = {[1812.08113] On The Chain Rule Optimal Transport Distance}, interhash = {5799ff852252e8083b24ae575497f420}, intrahash = {ef9011512b4baba8fea2615e2b24c28f}, keywords = {optimal-transport}, note = {cite arxiv:1812.08113Comment: 23 pages}, timestamp = {2019-12-11T14:20:51.000+0100}, title = {On The Chain Rule Optimal Transport Distance}, url = {http://arxiv.org/abs/1812.08113}, year = 2018 }