BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Virginia Tech//VT Calendar//EN
BEGIN:VEVENT
DTSTAMP:20210225T083000Z
UID:1614090951263@events.msu.edu
CATEGORIES:Conferences / Seminars / Lectures
DTSTART:20210225T083000Z
DTEND:20210225T093000Z
SUMMARY:Math Seminar Series
DESCRIPTION:
 Applied Mathematics\n
 \n
 Zaiwen Wen, Peking University, 
 China, will be speaking.\n
 \n
 The presentation 
 is titled "Stochastic Second-Order Methods 
 For Deep Learning."\n
 \n
 Contact Olga Turanova 
 (turanova@msu.edu) for more information.\n
 \n
 Stochastic 
 methods are widely used in deep 
 learning. In this talk, we first review the 
 state-of-the-art methods such as KFAC. Then 
 we present a structured stochastic quasi-Newton 
 method and a sketchy empirical natural gradient 
 method. Numerical results on deep convolution 
 networks illustrate that our methods 
 are quite competitive to SGD and KFAC.\n\n
 Price: free\n
 Sponsor: Department of Mathematics\n
 Sponsor's Homepage: https://www.math.msu.edu/\n
 Contact name: Department of Mathematics\n
 Contact phone: (517) 353-0844\n
 for more info visit the web at:\n 
 https://www.math.msu.edu/Seminars/CalendarView.aspx?month-of=September2016\n
LOCATION:Online via Zoom
END:VEVENT
END:VCALENDAR