Search Results for author:
Found 4 papers, 1 papers with code
Fast exploration and learning of latent graphs with aliased observations
We consider the problem of recovering a latent graph where the observations at each node are \emph{aliased}, and transitions are stochastic.
Graph schemas as abstractions for transfer learning, inference, and planning
Graph schemas can be learned in far fewer episodes than previous baselines, and can model and plan in a few steps in novel variations of these tasks.
Max-Sliced Wasserstein Distance and its use for GANs
Generative adversarial nets (GANs) and variational auto-encoders have significantly improved our distribution modeling capabilities, showing promise for dataset augmentation, image-to-image translation and feature learning.
Generative Modeling using the Sliced Wasserstein Distance
While this is particularly true for early GAN formulations, there has been significant empirically motivated and theoretically founded progress to improve stability, for instance, by using the Wasserstein distance rather than the Jenson-Shannon divergence.
