Loading Events
  • This event has passed.
Stochastics and Statistics Seminar

Fitting a putative manifold to noisy data

May 25, 2018 @ 11:00 am - 12:00 pm

Hariharan Narayanan (Tata Institute of Fundamental Research, Mumbai)


Abstract: We give a solution to the following question from manifold learning.
Suppose data belonging to a high dimensional Euclidean space is drawn independently, identically distributed from a measure supported on a low dimensional twice differentiable embedded compact manifold M, and is corrupted by a small amount of i.i.d gaussian noise. How can we produce a manifold M whose Hausdorff distance to M is small and whose reach (normal injectivity radius) is not much smaller than the reach of M?
This is joint work with Charles Fefferman, Sergei Ivanov, Yaroslav Kurylev, and Matti Lassas.

© MIT Statistics + Data Science Center | 77 Massachusetts Avenue | Cambridge, MA 02139-4307 | 617-253-1764 |