Fitting a putative manifold to noisy data

Charles Fefferman, Sergei Ivanov, Yaroslav Kurylev, Matti Lassas, Hariharan Narayanan

Research output: Contribution to journalConference articlepeer-review

20 Scopus citations

Abstract

In the present work, 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 manifold M, and corrupted by a small amount of gaussian noise.

Original languageEnglish (US)
Pages (from-to)688-720
Number of pages33
JournalProceedings of Machine Learning Research
Volume75
StatePublished - 2018
Event31st Annual Conference on Learning Theory, COLT 2018 - Stockholm, Sweden
Duration: Jul 6 2018Jul 9 2018

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Keywords

  • Hausdorff distance
  • Manifold learning
  • reach

Fingerprint

Dive into the research topics of 'Fitting a putative manifold to noisy data'. Together they form a unique fingerprint.

Cite this