Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms

24 December 2020

Papers citing "Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms"

34 / 34 papers shown

Title
When Deep Learning Meets Polyhedral Theory: A Survey Joey Huchette Gonzalo Muñoz Thiago Serra Calvin Tsay AI4CE 115 36 0 29 Apr 2023
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions Aaron Mishkin Arda Sahiner Mert Pilanci OffRL 87 30 0 02 Feb 2022
Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs Tolga Ergen Mert Pilanci OffRL MLT 49 33 0 11 Oct 2021
Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions Arda Sahiner Tolga Ergen Batu Mehmet Ozturkler Burak Bartan John M. Pauly Morteza Mardani Mert Pilanci GAN 43 20 0 12 Jul 2021
Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization Tolga Ergen Arda Sahiner Batu Mehmet Ozturkler John M. Pauly Morteza Mardani Mert Pilanci 45 32 0 02 Mar 2021
Convex Regularization Behind Neural Reconstruction Arda Sahiner Morteza Mardani Batu Mehmet Ozturkler Mert Pilanci John M. Pauly 44 25 0 09 Dec 2020
Nonparametric Learning of Two-Layer ReLU Residual Units Zhunxuan Wang Linyun He Chunchuan Lyu Shay B. Cohen MLT OffRL 77 1 0 17 Aug 2020
Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time Tolga Ergen Mert Pilanci 32 9 0 26 Jun 2020
Convex Geometry and Duality of Over-parameterized Neural Networks Tolga Ergen Mert Pilanci MLT 60 56 0 25 Feb 2020
Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks Mert Pilanci Tolga Ergen 49 118 0 24 Feb 2020
Revealing the Structure of Deep Neural Networks via Convex Duality Tolga Ergen Mert Pilanci MLT 29 71 0 22 Feb 2020
Global Convergence of Frank Wolfe on One Hidden Layer Networks Alexandre d’Aspremont Mert Pilanci 29 4 0 06 Feb 2020
PyTorch: An Imperative Style, High-Performance Deep Learning Library Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury ... Sasank Chilamkurthy Benoit Steiner Lu Fang Junjie Bai Soumith Chintala ODL 106 42,038 0 03 Dec 2019
Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence Aditya Golatkar Alessandro Achille Stefano Soatto 47 95 0 30 May 2019
On Dropout and Nuclear Norm Regularization Poorya Mianjy R. Arora 111 23 0 28 May 2019
On Exact Computation with an Infinitely Wide Neural Net Sanjeev Arora S. Du Wei Hu Zhiyuan Li Ruslan Salakhutdinov Ruosong Wang 118 915 0 26 Apr 2019
How do infinite width bounded norm networks look in function space? Pedro H. P. Savarese Itay Evron Daniel Soudry Nathan Srebro 30 166 0 13 Feb 2019
Convex Relaxations of Convolutional Neural Nets Burak Bartan Mert Pilanci 69 5 0 31 Dec 2018
Greedy Layerwise Learning Can Scale to ImageNet Eugene Belilovsky Michael Eickenberg Edouard Oyallon 72 180 0 29 Dec 2018
Learning Two-layer Neural Networks with Symmetric Inputs Rong Ge Rohith Kuditipudi Zhize Li Xiang Wang OOD MLT 82 57 0 16 Oct 2018
On the Implicit Bias of Dropout Poorya Mianjy R. Arora René Vidal 39 66 0 26 Jun 2018
Neural Tangent Kernel: Convergence and Generalization in Neural Networks Arthur Jacot Franck Gabriel Clément Hongler 134 3,160 0 20 Jun 2018
Decorrelated Batch Normalization Lei Huang Dawei Yang B. Lang Jia Deng 27 192 0 23 Apr 2018
Implicit Regularization in Matrix Factorization Suriya Gunasekar Blake E. Woodworth Srinadh Bhojanapalli Behnam Neyshabur Nathan Srebro 52 490 0 25 May 2017
Geometry of Factored Nuclear Norm Regularization Qiuwei Li Zhihui Zhu Gongguo Tang 17 24 0 05 Apr 2017
Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs Alon Brutzkus Amir Globerson MLT 63 313 0 26 Feb 2017
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification Kaiming He Xinming Zhang Shaoqing Ren Jian Sun VLM 95 18,534 0 06 Feb 2015
Adam: A Method for Stochastic Optimization Diederik P. Kingma Jimmy Ba ODL 421 149,474 0 22 Dec 2014
In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning Behnam Neyshabur Ryota Tomioka Nathan Srebro AI4CE 41 655 0 20 Dec 2014
Exact and Heuristic Algorithms for Semi-Nonnegative Matrix Factorization Nicolas Gillis Abhishek Kumar 47 33 0 27 Oct 2014
Matrix Completion and Low-Rank SVD via Fast Alternating Least Squares Trevor Hastie Rahul Mazumder Jason D. Lee R. Zadeh 46 522 0 09 Oct 2014
Trace Lasso: a trace norm regularization for correlated designs Edouard Grave G. Obozinski Francis R. Bach 73 196 0 09 Sep 2011
A New Approach to Collaborative Filtering: Operator Estimation with Spectral Regularization Jacob D. Abernethy Francis R. Bach Theodoros Evgeniou Jean-Philippe Vert 130 261 0 11 Feb 2008
Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization Benjamin Recht Maryam Fazel P. Parrilo 151 3,758 0 28 Jun 2007