no code implementations • 13 Feb 2022 • Qinxun Bai, Steven Rosenberg, Wei Xu
While natural gradients have been widely studied from both theoretical and empirical perspectives, we argue that some fundamental theoretical issues regarding the existence of gradients in infinite dimensional function spaces remain underexplored.
no code implementations • 3 Nov 2020 • Satoshi Egi, Yoshiaki Maeda, Steven Rosenberg
We study the diffeomorphism and isometry groups of manifolds $\overline {M_p}$, $p\in\mathbb Z$, which are circle bundles over a closed $4n$-dimensional integral symplectic manifold.
Differential Geometry
no code implementations • 14 Apr 2020 • Chaitanya Poolla, Abraham K. Ishihara, Dan Liddell, Rodney Martin, Steven Rosenberg
By augmenting the visual feedback in the university environment with a monetary incentive, the mean energy reduction was found to be ~24. 22%
2 code implementations • 9 Apr 2020 • Nathaniel Josephs, Lizhen Lin, Steven Rosenberg, Eric D. Kolaczyk
While the study of a single network is well-established, technological advances now allow for the collection of multiple networks with relative ease.
Applications
no code implementations • 25 Jan 2019 • Dara Gold, Steven Rosenberg
Manifold learning/dimensionality reduction, which seeks a low dimensional manifold that best represents data in a high dimensional Euclidean space, is an inherently infinite dimensional problem.
Dimensionality Reduction Differential Geometry
no code implementations • 4 Mar 2015 • Qinxun Bai, Steven Rosenberg, Zheng Wu, Stan Sclaroff
We study the problem of supervised learning for both binary and multiclass classification from a unified geometric perspective.