no code implementations • 25 Jan 2018 • Diego A. Mesa, Justin Tantiongloc, Marcela Mendoza, Todd P. Coleman
We also leverage findings from nonequilibrium thermodynamics to represent the transport map as a composition of simpler maps, each of which is learned sequentially with a transport cost regularized version of the aforementioned problem formulation.
no code implementations • 29 Sep 2015 • Sanggyun Kim, Diego Mesa, Rui Ma, Todd P. Coleman
We demonstrate with optimal transport theory that when the source distribution can be easily sampled from and the target distribution is log-concave, this can be tractably solved with convex optimization.
no code implementations • 9 Apr 2012 • Christopher J. Quinn, Negar Kiyavash, Todd P. Coleman
We show that under appropriate conditions, it is unique and consistent with another type of graphical model, the directed information graph, which is based on a generalization of Granger causality.