[AI Seminar] AI Seminar sponsored by Apple -- Simon Du -- March 27

[Adams Wei Yu]

Dear faculty and students,

We look forward to seeing you next Tuesday, March 27, at noon in *GHC 6115
(unusual place) *for AI Seminar sponsored by Apple. To learn more about the
seminar series, please visit the AI Seminar webpage
<http://www.cs.cmu.edu/~aiseminar/>.

On Tuesday,  Simon Du <http://www.cs.cmu.edu/~ssdu/> will give the
following talk:

Title:  On the Power of Randomly Initialized Gradient Descent for Learning
Convolutional Neural Networks

Abstract:

Convolutional neural networks trained by randomly initialized (stochastic)
gradient descent have achieved the state-of-art performances in many
applications. However, its theoretical properties remain elusive from an
optimization point of view. In this talk, I will present two results on
explaining the success of gradient descent.

In the first part, I will show under certain structural conditions of the
input distribution, randomly initialized gradient descent provably learns a
convolutional filter with ReLU activation and average pooling. This is the
first recovery guarantee of gradient-based algorithms for learning a
convolutional filter on general input distributions.

In the second part of the talk, I will show if the input distribution is
Gaussian, then randomly initialized gradient descent with
weight-normalization learns a ReLU activated one-hidden-layer convolutional
neural network where both the convolutional weights and the output weights
are to be optimized. To the best our knowledge, this is the first recovery
guarantee of randomly initialized gradient-based algorithms for neural
networks that contain more than one layers to be learned.

This talk is based on works with Jason D. Lee, Barnabas Poczos, Aarti Singh
and Yuandong Tian.


Bio:
Simon Shaolei Du is a PhD student in the Machine Learning Department at the
School of Computer Science, Carnegie Mellon University, advised by
Professor Aarti Singh and Professor Barnabas Poczos. His research interests
broadly include topics in theoretical machine learning and statistics, such
as deep learning, matrix factorization, convex/non-convex optimization,
transfer learning, reinforcement learning, non-parametric statistics and
robust statistics. Currently he is also developing methods for precision
agriculture. In 2011, he earned his high school degree from The
Experimental High School Attached to Beijing Normal University. In 2015, he
obtained his B.S. in Engineering Math & Statistics and B.S. in Electrical
Engineering & Computer Science from University of California, Berkeley. He
has also spent time working at research labs of Microsoft and Facebook.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-announce/attachments/20180324/599508dd/attachment.html>