Forthcoming seminars
Seminar calendar
List of seminars
Archive by years
Register a seminar

Forthcoming seminars

You may need the following programs to see the files

Colloquium of Steklov Mathematical Institute of Russian Academy of Sciences
December 5, 2019 16:00, Moscow, Steklov Mathematical Institute of RAS, Conference Hall (8 Gubkina)

Statistical Problems of Manifold Learning for Predictive Modeling

E. V. Burnaev

Skolkovo Institute of Science and Technology
Video records:
MP4 3,143.7 Mb
MP4 1,533.9 Mb

Number of views:
This page:858
Video files:357
Youtube Video:

E. V. Burnaev
Photo Gallery

Видео не загружается в Ваш браузер:
  1. Установите Adobe Flash Player    

  2. Проверьте с Вашим администратором, что из Вашей сети разрешены исходящие соединения на порт 8080
  3. Сообщите администратору портала о данной ошибке

Abstract: Predictive Modeling tasks deal with high-dimensional data, and curse of dimensionality is an obstacle to the use of many methods for their solutions. In many applications, real-world data occupy only a very small part of high-dimensional observation space whose intrinsic dimension is essentially lower than dimension of the space. Popular model for such data is a Manifold one in accordance with which data lie on or near an unknown low-dimensional Data manifold (DM) embedded in an ambient high-dimensional space. Predictive Modeling tasks studied under this assumption are referred to as the manifold learning ones whose general goal is discovering a low-dimensional structure of high-dimensional manifold valued data from a given dataset. If dataset points are sampled according to an unknown probability measure on the DM, we face with statistical problems about manifold valued data. In the talk we will provide a short review of statistical problems regarding high-dimensional manifold valued data and their solutions.

SHARE: FaceBook Twitter Livejournal
Contact us:
 Terms of Use  Registration  Logotypes © Steklov Mathematical Institute RAS, 2021