Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration

10 February 2020

Bindya Venkatesh

Jayaraman J. Thiagarajan

Kowshik Thopalli

P. Sattigeri

ArXiv PDF HTML

Papers citing "Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration"

25 / 25 papers shown

Title
What's Hidden in a Randomly Weighted Neural Network? Vivek Ramanujan Mitchell Wortsman Aniruddha Kembhavi Ali Farhadi Mohammad Rastegari 35 354 0 29 Nov 2019
Rigging the Lottery: Making All Tickets Winners Utku Evci Trevor Gale Jacob Menick Pablo Samuel Castro Erich Elsen 90 592 0 25 Nov 2019
ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring David Berthelot Nicholas Carlini E. D. Cubuk Alexey Kurakin Kihyuk Sohn Han Zhang Colin Raffel 59 676 0 21 Nov 2019
Evaluating Lottery Tickets Under Distributional Shifts Shrey Desai Hongyuan Zhan Ahmed Aly UQCV OOD 23 41 0 28 Oct 2019
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning Eric Arazo Diego Ortego Paul Albert Noel E. O'Connor Kevin McGuinness 66 826 0 08 Aug 2019
Sparse Networks from Scratch: Faster Training without Losing Performance Tim Dettmers Luke Zettlemoyer 54 337 0 10 Jul 2019
Weight Agnostic Neural Networks Adam Gaier David R Ha OOD 48 240 0 11 Jun 2019
One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers Ari S. Morcos Haonan Yu Michela Paganini Yuandong Tian 30 228 0 06 Jun 2019
On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks S. Thulasidasan Gopinath Chennupati J. Bilmes Tanmoy Bhattacharya S. Michalak UQCV 50 535 0 27 May 2019
Sparse Transfer Learning via Winning Lottery Tickets Rahul Mehta UQCV 31 45 0 19 May 2019
MixMatch: A Holistic Approach to Semi-Supervised Learning David Berthelot Nicholas Carlini Ian Goodfellow Nicolas Papernot Avital Oliver Colin Raffel 112 3,009 0 06 May 2019
Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask Hattie Zhou Janice Lan Rosanne Liu J. Yosinski UQCV 27 386 0 03 May 2019
Measuring Calibration in Deep Learning Jeremy Nixon Michael W. Dusenberry Ghassen Jerfel Timothy Nguyen Jeremiah Zhe Liu Linchuan Zhang Dustin Tran UQCV 47 484 0 02 Apr 2019
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations Dan Hendrycks Thomas G. Dietterich OOD VLM 60 3,399 0 28 Mar 2019
Learning for Single-Shot Confidence Calibration in Deep Neural Networks through Stochastic Inferences Seonguk Seo Paul Hongsuck Seo Bohyung Han FedML UQCV BDL 79 75 0 28 Sep 2018
Adaptive Network Sparsification with Dependent Variational Beta-Bernoulli Dropout Juho Lee Saehoon Kim Jaehong Yoon Haebeom Lee Eunho Yang Sung Ju Hwang 26 12 0 28 May 2018
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks Jonathan Frankle Michael Carbin 128 3,433 0 09 Mar 2018
mixup: Beyond Empirical Risk Minimization Hongyi Zhang Moustapha Cissé Yann N. Dauphin David Lopez-Paz NoLa 212 9,687 0 25 Oct 2017
To prune, or not to prune: exploring the efficacy of pruning for model compression Michael Zhu Suyog Gupta 98 1,262 0 05 Oct 2017
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms Han Xiao Kashif Rasul Roland Vollgraf 79 8,807 0 25 Aug 2017
On Calibration of Modern Neural Networks Chuan Guo Geoff Pleiss Yu Sun Kilian Q. Weinberger UQCV 142 5,774 0 14 Jun 2017
Variational Dropout Sparsifies Deep Neural Networks Dmitry Molchanov Arsenii Ashukha Dmitry Vetrov BDL 56 825 0 19 Jan 2017
Deep Residual Learning for Image Recognition Kaiming He Xinming Zhang Shaoqing Ren Jian Sun MedIm 961 192,638 0 10 Dec 2015
Adam: A Method for Stochastic Optimization Diederik P. Kingma Jimmy Ba ODL 385 149,474 0 22 Dec 2014
Very Deep Convolutional Networks for Large-Scale Image Recognition Karen Simonyan Andrew Zisserman FAtt MDE 616 99,991 0 04 Sep 2014