Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Mingchen Li, Mahdi Soltanolkotabi, Samet Oymak. Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks. In Silvia Chiappa, Roberto Calandra, editors, The 23rd International Conference on Artificial Intelligence and Statistics, AISTATS 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy]. Volume 108 of Proceedings of Machine Learning Research, pages 4313-4324, PMLR, 2020. [doi]

This author has not been identified. Look up 'Mingchen Li' in GoogleThis author has not been identified. Look up 'Mahdi Soltanolkotabi' in GoogleThis author has not been identified. Look up 'Samet Oymak' in Google

runs on WebDSL