no code implementations • 17 Mar 2020 • Colin B. Hansen, Vishwesh Nath, Diego A. Mesa, Yuankai Huo, Bennett A. Landman, Thomas A. Lasko
But in some learning problems, partial label information can be inferred from otherwise unlabeled examples and used to further improve the model.
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.