Search Results for author:
Found 5 papers, 2 papers with code
Adversarial Data Augmentation via Deformation Statistics
Data augmentation or semi-supervised approaches are commonly used to cope with limited labeled training data.
Optimal Transport Features for Morphometric Population Analysis
We demonstrate the proposed optimal transport feature extraction step in the context of a volumetric morphometric analysis of the OASIS-1 study for Alzheimer's disease.
Saddlepoints in Unsupervised Least Squares
This paper sheds light on the risk landscape of unsupervised least squares in the context of deep auto-encoding neural nets.
Multiscale Strategies for Computing Optimal Transport
The approach is based on an adaptive multiscale decomposition of the point sets.
Learning Multiple Tasks using Manifold Regularization
We present a novel method for multitask learning (MTL) based on {\it manifold regularization}: assume that all task parameters lie on a manifold.
