v1v2v3 (latest)

Variational Dropout Sparsifies Deep Neural Networks

International Conference on Machine Learning (ICML), 2017

19 January 2017

Dmitry Vetrov

Papers citing "Variational Dropout Sparsifies Deep Neural Networks"

31 / 481 papers shown

Title
Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation Manuel Haussmann Fred Hamprecht M. Kandemir BDL 137 6 0 19 May 2018
Nonparametric Bayesian Deep Networks with Local Competition Konstantinos P. Panousis S. Chatzis Sergios Theodoridis BDL 168 32 0 19 May 2018
Siamese Capsule Networks J. Ó. Neill 3DPC 106 8 0 18 May 2018
UNIQ: Uniform Noise Injection for Non-Uniform Quantization of Neural Networks Chaim Baskin Eli Schwartz Evgenii Zheltonozhskii Natan Liss Raja Giryes A. Bronstein A. Mendelson MQ 311 43 0 29 Apr 2018
A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers Tianyun Zhang Shaokai Ye Kaiqi Zhang Jian Tang Wujie Wen M. Fardad Yanzhi Wang 200 456 0 10 Apr 2018
FeTa: A DCA Pruning Algorithm with Generalization Error Guarantees Konstantinos Pitas Mike Davies P. Vandergheynst 88 2 0 12 Mar 2018
Variance Networks: When Expectation Does Not Meet Your ExpectationsInternational Conference on Learning Representations (ICLR), 2018 Kirill Neklyudov Dmitry Molchanov Arsenii Ashukha Dmitry Vetrov UQCV 322 24 0 10 Mar 2018
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks Jonathan Frankle Michael Carbin 872 3,872 0 09 Mar 2018
Synthesizing Neural Network Controllers with Probabilistic Model based Reinforcement Learning J. A. G. Higuera David Meger Gregory Dudek BDL 146 40 0 06 Mar 2018
Compressing Neural Networks using the Variational Information BottleneckInternational Conference on Machine Learning (ICML), 2018 Bin Dai Chen Zhu David Wipf MLT 245 191 0 28 Feb 2018
Bayesian Incremental Learning for Deep Neural Networks Max Kochurov T. Garipov D. Podoprikhin Dmitry Molchanov Arsenii Ashukha Dmitry Vetrov OOD CLL BDL 140 23 0 20 Feb 2018
Uncertainty Estimation via Stochastic Batch Normalization Andrei Atanov Arsenii Ashukha Dmitry Molchanov Kirill Neklyudov Dmitry Vetrov UQCV BDL 106 49 0 13 Feb 2018
Universal Deep Neural Network Compression Yoojin Choi Mostafa El-Khamy Jungwon Lee MQ 247 90 0 07 Feb 2018
TernaryNet: Faster Deep Model Inference without GPUs for Medical 3D Segmentation using Sparse and Binary Convolutions M. Heinrich Maximilian Blendowski Ozan Oktay MedIm 140 41 0 29 Jan 2018
Overpruning in Variational Bayesian Neural Networks Brian L. Trippe Richard Turner BDL 135 53 0 18 Jan 2018
StressedNets: Efficient Feature Representations via Stress-induced Evolutionary Synthesis of Deep Neural Networks M. Shafiee Brendan Chwyl Francis Li Rongyan Chen Michelle Karg C. Scharfenberger A. Wong 64 7 0 16 Jan 2018
Dropout Feature Ranking for Deep Learning Models C. Chang Ladislav Rampášek Anna Goldenberg OOD 140 52 0 22 Dec 2017
DropMax: Adaptive Variational SoftmaxNeural Information Processing Systems (NeurIPS), 2017 Haebeom Lee Juho Lee Saehoon Kim Eunho Yang Sung Ju Hwang 180 16 0 21 Dec 2017
Learning Sparse Neural Networks through $L_0$ Regularization Christos Louizos Max Welling Diederik P. Kingma 1.4K 1,226 0 04 Dec 2017
Probabilistic Adaptive Computation Time Michael Figurnov Artem Sobolev Dmitry Vetrov BDL 143 8 0 01 Dec 2017
Differentially Private Variational Dropout Beyza Ermis A. Cemgil 173 5 0 30 Nov 2017
Critical Learning Periods in Deep Neural Networks Alessandro Achille Matteo Rovere Stefano Soatto 170 112 0 24 Nov 2017
Improved Bayesian Compression Marco Federici Karen Ullrich Max Welling UQCV BDL 106 19 0 17 Nov 2017
Variational Gaussian Dropout is not Bayesian Jiri Hron A. G. Matthews Zoubin Ghahramani 105 48 0 08 Nov 2017
Bayesian Sparsification of Recurrent Neural Networks E. Lobacheva Nadezhda Chirkova Dmitry Vetrov UQCV BDL 182 16 0 31 Jul 2017
Emergence of Invariance and Disentanglement in Deep RepresentationsInformation Theory and Applications Workshop (ITA), 2017 Alessandro Achille Stefano Soatto OOD DRL 290 516 0 05 Jun 2017
Model Selection in Bayesian Neural Networks via Horseshoe PriorsJournal of machine learning research (JMLR), 2017 S. Ghosh Finale Doshi-Velez BDL 168 123 0 29 May 2017
Bayesian Compression for Deep Learning Christos Louizos Karen Ullrich Max Welling UQCV BDL 561 492 0 24 May 2017
Structured Bayesian Pruning via Log-Normal Multiplicative Noise Kirill Neklyudov Dmitry Molchanov Arsenii Ashukha Dmitry Vetrov BDL 247 191 0 20 May 2017
Multiplicative Normalizing Flows for Variational Bayesian Neural Networks Christos Louizos Max Welling BDL 311 484 0 06 Mar 2017
Soft Weight-Sharing for Neural Network CompressionInternational Conference on Learning Representations (ICLR), 2017 Karen Ullrich Edward Meeds Max Welling 356 433 0 13 Feb 2017