Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?

Samet Oymak, Mahdi Soltanolkotabi. Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?. In Kamalika Chaudhuri, Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA. Volume 97 of Proceedings of Machine Learning Research, pages 4951-4960, PMLR, 2019. [doi]

Abstract

Abstract is missing.