Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup

Sebastian Goldt, Madhu Advani, Andrew M. Saxe, Florent Krzakala, Lenka Zdeborová. Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup. In Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alché-Buc, Edward A. Fox, Roman Garnett, editors, Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada. pages 6979-6989, 2019. [doi]

Abstract

Abstract is missing.