no code implementations • 2 Jan 2024 • Scott Mahan, Caroline Moosmüller, Alexander Cloninger
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.
no code implementations • 22 Aug 2022 • Stefan C. Schonsheck, Scott Mahan, Timo Klock, Alexander Cloninger, Rongjie Lai
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.
no code implementations • 7 Jun 2021 • Scott Mahan, Henry Kvinge, Tim Doster
Building invariance to non-meaningful transformations is essential to building efficient and generalizable machine learning models.
1 code implementation • 23 Jul 2020 • Scott Mahan, Emily King, Alex Cloninger
Thus, sets of realized neural networks are not closed in order-$(m-1)$ Sobolev spaces $W^{m-1, p}$ for $p \in [1,\infty]$.