Abstract for the talk on 06.08.2020 (17:00 h)

Math Machine Learning seminar MPI MIS + UCLA

Simon S. Du (University of Washington)
Ultra-wide Neural Network and Neural Tangent Kernel
06.08.2020, 17:00 h, only video broadcast

I will talk about the result on the equivalence between the over-parameterized neural network and a new kernel, Neural Tangent Kernel. This equivalence implies two surprising phenomena: 1) the simple algorithm gradient descent provably finds the global optimum of the highly non-convex empirical risk, and 2) the learned neural network generalizes well despite being highly over-parameterized. I will also present empirical results showing Neural Tangent Kernel is a strong predictor.

If you want to participate in this video broadcast please register using this special form. The (Zoom) link for the video broadcast will be sent to your email address one day before the seminar.

30.07.2020, 16:11