1. Algorithmic regularization in over-parameterized matrix sensing and neural networks with quadratic activations;li;COLT,2018
2. Theoretical properties of the global optimizer of two layer neural network;boob;ArXiv Preprint,2017
3. The-oretical insights into the optimization landscape of over-parameterized shallow neural networks;soltanolkotabi;ArXiv Preprint,2017
4. Learning one-hidden-layer neural networks with landscape design;ge;ArXiv Preprint,2017
5. Diversity leads to generalization in neural networks;xie;ArXiv Preprint,2016