RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB
Forthcoming seminars
Seminar calendar
List of seminars
Archive by years
Register a seminar

Search
RSS
Forthcoming seminars





You may need the following programs to see the files








Joint Mathematical seminar of Saint Petersburg State University and Peking University
January 14, 2021 16:00–17:00, St. Petersburg, online
 


Exploring Stochastic Methods For Deep Learning and Reinforcement Learning

Zaiwen Wen

Beijing International Center for Mathematical Research

Number of views:
This page:26

Abstract: Stochastic methods are widely used in machine learning. In this talk, we present a structured stochastic quasi-Newton method and a sketchy empirical natural gradient method for deep learning. We also introduce a stochastic quadratic penalty algorithm for reinforcement learning.

Language: English

Website: https://zoom.com.cn/j/68067087375?pwd=MnlxYU1yV05BTnVrUzRQOHF6YUVBQT09

* Meeting ID:680 6708 7375 Password:313186

SHARE: VKontakte.ru FaceBook Twitter Mail.ru Livejournal Memori.ru
 
Contact us:
 Terms of Use  Registration  Logotypes © Steklov Mathematical Institute RAS, 2021