Machine Learning Seminar: Estimating a manifold from noisy samples
Sponsor(s): Machine Learning, Bass Connections-Information, Society & Culture, Biomedical Engineering (BME), Biostatistics and Bioinformatics, Computational Biology and Bioinformatics (CBB), Computer Science, Electrical and Computer Engineering (ECE), Information Initiative at Duke (iiD), Mathematics, Pratt School of Engineering, and Statistical Science
Estimating a manifold from (possibly noisy) samples appears to be a difficult problem. Indeed, even after decades of research, all manifold learning methods do not actually "learn" the manifold, but rather try to embed it into a low-dimensional Euclidean space. This process inevitably introduces distortions and cannot guarantee a robust estimate of the manifold.
In this talk, we will discuss a new method to estimate a manifold in ambient space, which is efficient even in the case of an ambient space of high dimension. The method gives a robust estimate to the manifold and its tangent, without introducing distortions. Moreover, we will show statistical convergence guarantees.
Contact: Ariel Dawn