Tianyi Liu, Yan Li, Song Wei, Enlu Zhou, Tuo Zhao. Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization. In Arindam Banerjee 0001, Kenji Fukumizu, editors, The 24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021, April 13-15, 2021, Virtual Event. Volume 130 of Proceedings of Machine Learning Research, pages 1891-1899, PMLR, 2021. [doi]
Abstract is missing.