Why are deep nets reversible: A simple theory, with implications for training

18 November 2015

Papers citing "Why are deep nets reversible: A simple theory, with implications for training"

12 / 12 papers shown

Title
Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks Dan Zhao 26 5 0 01 Jun 2023
Sub-Gaussian Matrices on Sets: Optimal Tail Dependence and Applications Halyun Jeong Xiaowei Li Y. Plan Özgür Yilmaz 24 18 0 28 Jan 2020
Robust One-Bit Recovery via ReLU Generative Networks: Near-Optimal Statistical Rate and Global Landscape Analysis Shuang Qiu Xiaohan Wei Zhuoran Yang 35 24 0 14 Aug 2019
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning Charles H. Martin Michael W. Mahoney AI4CE 52 193 0 02 Oct 2018
Analysis of Invariance and Robustness via Invertibility of ReLU-Networks Jens Behrmann Sören Dittmer Pascal Fernsel Peter Maass 30 12 0 25 Jun 2018
Rate-Optimal Denoising with Deep Neural Networks Reinhard Heckel Wen Huang Paul Hand V. Voroninski 30 23 0 22 May 2018
Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net Anirudh Goyal Nan Rosemary Ke Surya Ganguli Yoshua Bengio DiffM 35 55 0 07 Nov 2017
Reversible Architectures for Arbitrarily Deep Residual Neural Networks B. Chang Lili Meng E. Haber Lars Ruthotto David Begert E. Holtham AI4CE 36 261 0 12 Sep 2017
Towards Understanding the Invertibility of Convolutional Neural Networks A. Gilbert Yi Zhang Kibok Lee Y. Zhang Honglak Lee 19 64 0 24 May 2017
AdaNet: Adaptive Structural Learning of Artificial Neural Networks Corinna Cortes X. Gonzalvo Vitaly Kuznetsov M. Mohri Scott Yang 31 283 0 05 Jul 2016
Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation B. Scellier Yoshua Bengio 42 481 0 16 Feb 2016
On the interplay of network structure and gradient convergence in deep learning V. Ithapu Sathya Ravi Vikas Singh 23 3 0 17 Nov 2015