Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths

16 May 2022

Papers citing "Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths"

9 / 9 papers shown

Title
Global Convergence Rate of Deep Equilibrium Models with General Activations Lan V. Truong 67 2 0 11 Feb 2023
Stabilizing Equilibrium Models by Jacobian Regularization Shaojie Bai V. Koltun J. Zico Kolter 57 57 0 28 Jun 2021
Multiscale Deep Equilibrium Models Shaojie Bai V. Koltun J. Zico Kolter BDL 80 211 0 15 Jun 2020
Monotone operator equilibrium networks Ezra Winston J. Zico Kolter 51 130 0 15 Jun 2020
Implicit Deep Learning L. Ghaoui Fangda Gu Bertrand Travacca Armin Askari Alicia Y. Tsai AI4CE 54 178 0 17 Aug 2019
Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks Difan Zou Yuan Cao Dongruo Zhou Quanquan Gu ODL 156 448 0 21 Nov 2018
Gradient Descent Provably Optimizes Over-parameterized Neural Networks S. Du Xiyu Zhai Barnabás Póczós Aarti Singh MLT ODL 192 1,270 0 04 Oct 2018
Neural Ordinary Differential Equations T. Chen Yulia Rubanova J. Bettencourt David Duvenaud AI4CE 334 5,081 0 19 Jun 2018
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification Kaiming He Xinming Zhang Shaoqing Ren Jian Sun VLM 276 18,587 0 06 Feb 2015