Convergence Rates of Training Deep Neural Networks via Alternating
Minimization Methods

v1v2 (latest)

Convergence Rates of Training Deep Neural Networks via Alternating Minimization Methods

30 August 2022

ArXiv (abs)PDF HTML

Papers citing "Convergence Rates of Training Deep Neural Networks via Alternating Minimization Methods"

7 / 7 papers shown

Title
Fenchel Lifted Networks: A Lagrange Relaxation of Neural Network Training Fangda Gu Armin Askari L. Ghaoui 72 39 0 20 Nov 2018
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation Liang-Chieh Chen Yukun Zhu George Papandreou Florian Schroff Hartwig Adam SSeg 490 13,194 0 07 Feb 2018
Convergent Block Coordinate Descent for Training Tikhonov Regularized Deep Neural Networks Ziming Zhang M. Brand 54 71 0 20 Nov 2017
Wide & Deep Learning for Recommender Systems Heng-Tze Cheng L. Koc Jeremiah Harmsen T. Shaked Tushar Chandra ... Zakaria Haque Lichan Hong Vihan Jain Xiaobing Liu Hemal Shah HAI VLM 198 3,673 0 24 Jun 2016
Training Neural Networks Without Gradients: A Scalable ADMM Approach Gavin Taylor R. Burmeister Zheng Xu Bharat Singh Ankit B. Patel Tom Goldstein ODL 79 276 0 06 May 2016
Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods Guoyin Li Ting Kei Pong 162 296 0 09 Feb 2016
Sequence to Sequence Learning with Neural Networks Ilya Sutskever Oriol Vinyals Quoc V. Le AIMat 450 20,606 0 10 Sep 2014