Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound
arXiv:1906.03593
Abstract
We improve the over-parametrization size over two beautiful results [Li and Liang' 2018] and [Du, Zhai, Poczos and Singh' 2019] in deep learning theory.
arXiv:1906.03593
We improve the over-parametrization size over two beautiful results [Li and Liang' 2018] and [Du, Zhai, Poczos and Singh' 2019] in deep learning theory.