Search Results for author:
Found 4 papers, 1 papers with code
Point Cloud Classification via Deep Set Linearized Optimal Transport
Our approach is motivated by the observation that $L^2-$distances between optimal transport maps for distinct point clouds, originating from a shared fixed reference distribution, provide an approximation of the Wasserstein-2 distance between these point clouds, under certain assumptions.
Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoders
Our numerical experiments on synthetic and real-world data verify that the proposed model can effectively manage data with multi-class nearby but disjoint manifolds of different classes, overlapping manifolds, and manifolds with non-trivial topology.
Rotating spiders and reflecting dogs: a class conditional approach to learning data augmentation distributions
Building invariance to non-meaningful transformations is essential to building efficient and generalizable machine learning models.
Nonclosedness of Sets of Neural Networks in Sobolev Spaces
Thus, sets of realized neural networks are not closed in order-$(m-1)$ Sobolev spaces $W^{m-1, p}$ for $p \in [1,\infty]$.
