Return to Colloquia & Seminar listing
On using graph distances to estimate Euclidean and related distances
Mathematics of Data & Decisions| Speaker: | Ery Arias-Castro, UC San Diego |
| Related Webpage: | http://maddd.math.ucdavis.edu |
| Location: | 1147 MSB |
| Start time: | Mon, Oct 8 2018, 4:10PM |
Graph distances have proven quite useful in machine learning/statistics, particularly in the estimation of Euclidean or geodesic distances. The talk will include a partial review of the literature, and then present more recent developments on the estimation of curvature-constrained distances on a surface, as well as on the estimation of Euclidean distances based on an unweighted and noisy neighborhood graph.
(Joint work with Thibaut Le Gouic, Antoine Channarond, Bruno Pelletier, and Nicolas Verzelen.)