Lecture 1. Mini-course "Strong probability distances and limit theorems" (Sergey Bobkov)
677 views · Published 31 May 2018 · 2:40:55 · Indexed 16 November 2026
Channel: ФКН НИУ ВШЭ · 2018 · Education
The course explores strong distances in the space of probability distributions, including total variation, relative entropy, chi-squared and more general Renyi/Tsallis informational divergences, as well as relative Fisher information. Special attention is given to the distances from the normal law. Topics: - General theory of Renyi and Tsallis informational divergences. - Relative entropy and chi-squared distance as particular cases. - Relationship with a total variation. Pinsker-type inequalities. - Entropy power inequality. - Basic properties of relative entropy. - Fisher information. - Stam’s inequality and its applications. Lecturer: Sergey Bobkov, chief research fellow of the International Laboratory of Stochastic Algorithms and High-Dimensional Inference, University of Minnesota. Faculty of Computer Science: https://cs.hse.ru/en/ Follow us: https://www.facebook.com/hsefcs; https://twitter.com/CS_HSE
More from this channel
-
1:18:31
[Коллоквиум]: On scale invariance, multifractal formalism, and their applications
-
1:09:43
[Коллоквиум]: Resourse Allocation in the Cloud - Assaf Schuster, Techion
-
1:08:04
[ИТ-лекторий] Занимательная прикладная аналитика в Яндексе
-
1:17:41
[Коллоквиум]: Probabilistic graphical models: Factor graphs and more
-
1:05:46
[Коллоквиум]: Process Mining: Data Science in Action - Wil van der Aalst
-
2:18
[Презентация факультета в ДК ЗИЛ]: Григорий Бакунов, директор по распрост. инф. технологий Яндекс
-
2:55
[Презентация факультета в ДК ЗИЛ]: Григорий Канторович, проректор по работе с абитуриентами ВШЭ
-
11:34
[Презентация факультета в ДК ЗИЛ]: Иван Аржанцев, декан факультета компьютерных наук