1. Implicit convex regularizers of CNN architectures: Convex optimization of two- and three-layer networks in polynomial time;ergen;arXiv 2006 14798,2020
2. Neural networks are convex regularizers: Exact polynomial-time convex optimization formulations for two-layer networks;pilanci;Proc Int Conf Mach Learn,2020
3. Deep neural networks as Gaussian processes;lee;Proc Int Conf Learn Represent,2018
4. On learning over-parameterized neural networks: A functional approximation prospective;su;Advances in neural information processing systems,2019
5. Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks;arora;Proc Int Conf Mach Learn,2019