Gradient Descent can Learn Less Over-parameterized Two-layer Neural Networks on Classification Problems

23 May 2019

Papers citing "Gradient Descent can Learn Less Over-parameterized Two-layer Neural Networks on Classification Problems"

8 / 8 papers shown

Title
Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods Hossein Taheri Christos Thrampoulidis Arya Mazumdar MLT 33 0 0 13 Oct 2024
Fine-grained analysis of non-parametric estimation for pairwise learning Junyu Zhou Shuo Huang Han Feng Puyu Wang Ding-Xuan Zhou 40 1 0 31 May 2023
Generalization Guarantees of Gradient Descent for Multi-Layer Neural Networks Puyu Wang Yunwen Lei Di Wang Yiming Ying Ding-Xuan Zhou MLT 27 3 0 26 May 2023
When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work Jiawei Zhang Yushun Zhang Mingyi Hong Ruoyu Sun Z. Luo 26 10 0 21 Oct 2022
Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity Jianyi Yang Shaolei Ren 24 3 0 02 Jul 2022
Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis Alexander Munteanu Simon Omlor Zhao-quan Song David P. Woodruff 27 15 0 26 Jun 2022
A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective? Hiroaki Mikami Kenji Fukumizu Shogo Murai Shuji Suzuki Yuta Kikuchi Taiji Suzuki S. Maeda Kohei Hayashi 40 12 0 25 Aug 2021
The Interpolation Phase Transition in Neural Networks: Memorization and Generalization under Lazy Training Andrea Montanari Yiqiao Zhong 47 95 0 25 Jul 2020