Thursday, February 25, 2021
3:30am
to
4:30am
|
|
Math Seminar Series
(Conferences / Seminars / Lectures)
Applied Mathematics
Zaiwen Wen, Peking University, China, will be speaking.
The presentation is titled "Stochastic Second-Order Methods For Deep Learning."
Contact Olga Turanova (turanova@msu.edu) for more information.
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. more information...
|
(517) 353-0844
