The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective

10 October 2022

Papers citing "The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective"

50 / 52 papers shown

Title
Mitigating multiple descents: A model-agnostic framework for risk monotonization Pratik V. Patil Arun K. Kuchibhotla Yuting Wei Alessandro Rinaldo 80 8 0 25 May 2022
Masked Siamese Networks for Label-Efficient Learning Mahmoud Assran Mathilde Caron Ishan Misra Piotr Bojanowski Florian Bordes Pascal Vincent Armand Joulin Michael G. Rabbat Nicolas Ballas SSL 91 320 0 14 Apr 2022
Data Augmentation as Feature Manipulation Ruoqi Shen Sébastien Bubeck Suriya Gunasekar MLT 36 16 0 03 Mar 2022
Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation Yutong Dai Brian L. Price He Zhang Chunhua Shen 77 29 0 18 Jan 2022
Masked Autoencoders Are Scalable Vision Learners Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Dollár Ross B. Girshick ViT TPM 451 7,739 0 11 Nov 2021
Harmless interpolation in regression and classification with structured features Andrew D. McRae Santhosh Karnik Mark A. Davenport Vidya Muthukumar 132 11 0 09 Nov 2021
Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity Ran Liu Mehdi Azabou M. Dabagia Chi-Heng Lin M. G. Azar Keith B. Hengen Michal Valko Eva L. Dyer OCL SSL DRL 31 36 0 03 Nov 2021
A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning Yehuda Dar Vidya Muthukumar Richard G. Baraniuk 77 72 0 06 Sep 2021
Comparing Classes of Estimators: When does Gradient Descent Beat Ridge Regression in Linear Models? Dominic Richards Yan Sun Patrick Rebeschini 33 3 0 26 Aug 2021
A Survey of Data Augmentation Approaches for NLP Steven Y. Feng Varun Gangal Jason W. Wei Sarath Chandar Soroush Vosoughi Teruko Mitamura Eduard H. Hovy AIMat 98 823 0 07 May 2021
Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures Yuan Cao Quanquan Gu M. Belkin 36 52 0 28 Apr 2021
A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation Jianlong Yuan Yifan Liu Chunhua Shen Zhibin Wang Hao Li 45 112 0 15 Apr 2021
How rotational invariance of common kernels prevents generalization in high dimensions Konstantin Donhauser Mingqi Wu Fanny Yang 71 24 0 09 Apr 2021
Benign Overfitting of Constant-Stepsize SGD for Linear Regression Difan Zou Jingfeng Wu Vladimir Braverman Quanquan Gu Sham Kakade 44 63 0 23 Mar 2021
Barlow Twins: Self-Supervised Learning via Redundancy Reduction Jure Zbontar Li Jing Ishan Misra Yann LeCun Stéphane Deny SSL 300 2,344 0 04 Mar 2021
Learning with invariances in random features and kernel models Song Mei Theodor Misiakiewicz Andrea Montanari OOD 94 90 0 25 Feb 2021
Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction Mehdi Azabou M. G. Azar Ran Liu Chi-Heng Lin Erik C. Johnson ... Lindsey Kitchell Keith B. Hengen William R. Gray Roncal Michal Valko Eva L. Dyer AI4TS 63 57 0 19 Feb 2021
Negative Data Augmentation Abhishek Sinha Kumar Ayush Jiaming Song Burak Uzkent Hongxia Jin Stefano Ermon 72 74 0 09 Feb 2021
Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning Zeyuan Allen-Zhu Yuanzhi Li FedML 118 372 0 17 Dec 2020
Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting and Regularization Ke Wang Christos Thrampoulidis 57 28 0 18 Nov 2020
How Data Augmentation affects Optimization for Linear Regression Boris Hanin Yi Sun 57 16 0 21 Oct 2020
Benign overfitting in ridge regression Alexander Tsigler Peter L. Bartlett 66 167 0 29 Sep 2020
Bootstrap your own latent: A new approach to self-supervised Learning Jean-Bastien Grill Florian Strub Florent Altché Corentin Tallec Pierre Harvey Richemond ... M. G. Azar Bilal Piot Koray Kavukcuoglu Rémi Munos Michal Valko SSL 360 6,797 0 13 Jun 2020
Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks Like Hui M. Belkin UQCV AAML VLM 48 171 0 12 Jun 2020
$On the Optimal Weighted $\ell_2$ Regularization in Overparameterized Linear Regression$ On the Optimal Weighted $\ell_2$ Regularization in Overparameterized Linear Regression Denny Wu Ji Xu 65 122 0 10 Jun 2020
Classification vs regression in overparameterized regimes: Does the loss function matter? Vidya Muthukumar Adhyyan Narang Vignesh Subramanian M. Belkin Daniel J. Hsu A. Sahai 81 151 0 16 May 2020
On the Generalization Effects of Linear Transformations in Data Augmentation Sen Wu Hongyang R. Zhang Gregory Valiant Christopher Ré 54 77 0 02 May 2020
Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime Niladri S. Chatterji Philip M. Long 41 108 0 25 Apr 2020
Optimal Regularization Can Mitigate Double Descent Preetum Nakkiran Prayaag Venkat Sham Kakade Tengyu Ma 81 133 0 04 Mar 2020
Time Series Data Augmentation for Deep Learning: A Survey Qingsong Wen Liang Sun Fan Yang Xiaomin Song Jing Gao Xue Wang Huan Xu AI4TS 58 642 0 27 Feb 2020
A Simple Framework for Contrastive Learning of Visual Representations Ting-Li Chen Simon Kornblith Mohammad Norouzi Geoffrey E. Hinton SSL 358 18,752 0 13 Feb 2020
A Model of Double Descent for High-dimensional Binary Linear Classification Zeyu Deng A. Kammoun Christos Thrampoulidis 79 146 0 13 Nov 2019
Enhanced Convolutional Neural Tangent Kernels Zhiyuan Li Ruosong Wang Dingli Yu S. Du Wei Hu Ruslan Salakhutdinov Sanjeev Arora 62 132 0 03 Nov 2019
Benign Overfitting in Linear Regression Peter L. Bartlett Philip M. Long Gábor Lugosi Alexander Tsigler MLT 74 776 0 26 Jun 2019
Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness Fanny Yang Zuowen Wang C. Heinze-Deml 100 42 0 26 Jun 2019
Harmless interpolation of noisy data in regression Vidya Muthukumar Kailas Vodrahalli Vignesh Subramanian A. Sahai 74 202 0 21 Mar 2019
Surprises in High-Dimensional Ridgeless Least Squares Interpolation Trevor Hastie Andrea Montanari Saharon Rosset Robert Tibshirani 184 743 0 19 Mar 2019
Two models of double descent for weak features M. Belkin Daniel J. Hsu Ji Xu 90 374 0 18 Mar 2019
Reconciling modern machine learning practice and the bias-variance trade-off M. Belkin Daniel J. Hsu Siyuan Ma Soumik Mandal 227 1,647 0 28 Dec 2018
Deep Knockoffs Yaniv Romano Matteo Sesia Emmanuel J. Candès BDL 65 140 0 16 Nov 2018
On the Implicit Bias of Dropout Poorya Mianjy R. Arora René Vidal 52 67 0 26 Jun 2018
Optimal ridge penalty for real-world high-dimensional data can be zero or negative due to the implicit ridge regularization D. Kobak Jonathan Lomond Benoit Sanchez 52 89 0 28 May 2018
A Kernel Theory of Modern Data Augmentation Tri Dao Albert Gu Alexander J. Ratner Virginia Smith Christopher De Sa Christopher Ré 100 193 0 16 Mar 2018
mixup: Beyond Empirical Risk Minimization Hongyi Zhang Moustapha Cissé Yann N. Dauphin David Lopez-Paz NoLa 276 9,760 0 25 Oct 2017
Dropout as a Low-Rank Regularizer for Matrix Factorization Jacopo Cavazza Pietro Morerio B. Haeffele Connor Lane Vittorio Murino René Vidal 106 42 0 13 Oct 2017
Learning to Compose Domain-Specific Transformations for Data Augmentation Alexander J. Ratner Henry R. Ehrenberg Zeshan Hussain Jared A. Dunnmon Christopher Ré 70 349 0 06 Sep 2017
Improved Regularization of Convolutional Neural Networks with Cutout Terrance Devries Graham W. Taylor 109 3,764 0 15 Aug 2017
Local Group Invariant Representations via Orbit Embeddings Anant Raj Abhishek Kumar Youssef Mroueh Tom Fletcher Bernhard Schölkopf 48 38 0 06 Dec 2016
Group Equivariant Convolutional Networks Taco S. Cohen Max Welling BDL 167 1,934 0 24 Feb 2016
Dropout as data augmentation Xavier Bouthillier K. Konda Pascal Vincent Roland Memisevic 73 134 0 29 Jun 2015