Simon S. Du (University of Washington): Ultra-wide Neural Network and Neural Tangent Kernel
Ort: MPI für Mathematik in den Naturwissenschaften Leipzig, , Videobroadcast
Video broadcast: Math Machine Learning seminar MPI MIS + UCLA 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.
Beginn: Aug. 6, 2020, 5 p.m.
Ende: Aug. 6, 2020, 6:30 p.m.