The Pitfalls of Simplicity Bias in Neural Networks

13 June 2020

Harshay Shah

Papers citing "The Pitfalls of Simplicity Bias in Neural Networks"

50 / 84 papers shown

Title
Fine-Grained Bias Exploration and Mitigation for Group-Robust Classification Miaoyun Zhao Qiang Zhang C. Li 48 0 0 11 May 2025
Severing Spurious Correlations with Data Pruning Varun Mulchandani Jung-Eun Kim 347 0 0 24 Mar 2025
Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization Simone Bombari Marco Mondelli 163 0 0 03 Feb 2025
Refining Skewed Perceptions in Vision-Language Models through Visual Representations Haocheng Dai Sarang Joshi VLM 88 0 0 03 Jan 2025
The Silent Majority: Demystifying Memorization Effect in the Presence of Spurious Correlations Chenyu You Haocheng Dai Yifei Min Jasjeet Sekhon S. Joshi James S. Duncan 79 3 0 01 Jan 2025
Aligning Generalisation Between Humans and Machines Filip Ilievski Barbara Hammer F. V. Harmelen Benjamin Paassen S. Saralajew ... Vered Shwartz Gabriella Skitalinskaya Clemens Stachl Gido M. van de Ven T. Villmann 176 1 0 23 Nov 2024
Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture Sajad Movahedi Antonio Orvieto Seyed-Mohsen Moosavi-Dezfooli AI4CE AAML 362 0 0 15 Oct 2024
SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning Hojoon Lee Dongyoon Hwang Donghu Kim Hyunseung Kim Jun Jet Tai K. Subramanian Peter R. Wurman Jaegul Choo Peter Stone Takuma Seno OffRL 98 12 0 13 Oct 2024
Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks Amit Peleg Matthias Hein 39 0 0 04 Jul 2024
Feature contamination: Neural networks learn uncorrelated features and fail to generalize Tianren Zhang Chujie Zhao Guanyu Chen Yizhou Jiang Feng Chen OOD MLT OODD 134 4 0 05 Jun 2024
When does compositional structure yield compositional generalization? A kernel theory Samuel Lippl Kim Stachenfeld NAI CoGe 115 8 0 26 May 2024
Neural Redshift: Random Networks are not Random Functions Damien Teney A. Nicolicioiu Valentin Hartmann Ehsan Abbasnejad 112 22 0 04 Mar 2024
What shapes feature representations? Exploring datasets, architectures, and training Katherine L. Hermann Andrew Kyle Lampinen OOD 37 156 0 22 Jun 2020
Evaluating Models' Local Decision Boundaries via Contrast Sets Matt Gardner Yoav Artzi Victoria Basmova Jonathan Berant Ben Bogin ... Sanjay Subramanian Reut Tsarfaty Eric Wallace Ally Zhang Ben Zhou ELM 51 84 0 06 Apr 2020
Hold me tight! Influence of discriminative features on deep network boundaries Guillermo Ortiz-Jiménez Apostolos Modas Seyed-Mohsen Moosavi-Dezfooli P. Frossard AAML 22 50 0 15 Feb 2020
Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss Lénaïc Chizat Francis R. Bach MLT 56 332 0 11 Feb 2020
Fast is better than free: Revisiting adversarial training Eric Wong Leslie Rice J. Zico Kolter AAML OOD 118 1,167 0 12 Jan 2020
Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging Luke Oakden-Rayner Jared A. Dunnmon G. Carneiro Christopher Ré OOD 48 380 0 27 Sep 2019
Natural Adversarial Examples Dan Hendrycks Kevin Zhao Steven Basart Jacob Steinhardt D. Song OODD 153 1,454 0 16 Jul 2019
Kernel and Rich Regimes in Overparametrized Models Blake E. Woodworth Suriya Gunasekar Pedro H. P. Savarese E. Moroshko Itay Golan Jason D. Lee Daniel Soudry Nathan Srebro 51 358 0 13 Jun 2019
Intriguing properties of adversarial training at scale Cihang Xie Alan Yuille AAML 35 68 0 10 Jun 2019
Likelihood Ratios for Out-of-Distribution Detection Jie Jessie Ren Peter J. Liu Emily Fertig Jasper Snoek Ryan Poplin M. DePristo Joshua V. Dillon Balaji Lakshminarayanan OODD 102 717 0 07 Jun 2019
Learning Robust Global Representations by Penalizing Local Predictive Power Haohan Wang Songwei Ge Eric Xing Zachary Chase Lipton OOD 73 944 0 29 May 2019
SGD on Neural Networks Learns Functions of Increasing Complexity Preetum Nakkiran Gal Kaplun Dimitris Kalimeris Tristan Yang Benjamin L. Edelman Fred Zhang Boaz Barak MLT 115 242 0 28 May 2019
Adversarial Examples Are Not Bugs, They Are Features Andrew Ilyas Shibani Santurkar Dimitris Tsipras Logan Engstrom Brandon Tran Aleksander Madry SILM 68 1,825 0 06 May 2019
Adversarial Training for Free! Ali Shafahi Mahyar Najibi Amin Ghiasi Zheng Xu John P. Dickerson Christoph Studer L. Davis Gavin Taylor Tom Goldstein AAML 97 1,238 0 29 Apr 2019
GradMask: Reduce Overfitting by Regularizing Saliency B. Simpson Francis Dutil Yoshua Bengio Joseph Paul Cohen MedIm 33 24 0 16 Apr 2019
Unrestricted Adversarial Examples via Semantic Manipulation Anand Bhattad Min Jin Chong Kaizhao Liang Yangqiu Song David A. Forsyth AAML 46 151 0 12 Apr 2019
Learning Robust Representations by Projecting Superficial Statistics Out Haohan Wang Zexue He Zachary Chase Lipton Eric Xing OOD 48 234 0 02 Mar 2019
The Odds are Odd: A Statistical Test for Detecting Adversarial Examples Kevin Roth Yannic Kilcher Thomas Hofmann AAML 36 175 0 13 Feb 2019
Uniform convergence may be unable to explain generalization in deep learning Vaishnavh Nagarajan J. Zico Kolter MoMe AI4CE 39 314 0 13 Feb 2019
Computational Limitations in Robust Classification and Win-Win Results Akshay Degwekar Preetum Nakkiran Vinod Vaikuntanathan 20 38 0 04 Feb 2019
Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference R. Thomas McCoy Ellie Pavlick Tal Linzen 94 1,226 0 04 Feb 2019
Improving Adversarial Robustness of Ensembles with Diversity Training Sanjay Kariyappa Moinuddin K. Qureshi AAML FedML 28 134 0 28 Jan 2019
Improving Adversarial Robustness via Promoting Ensemble Diversity Tianyu Pang Kun Xu Chao Du Ning Chen Jun Zhu AAML 50 435 0 25 Jan 2019
Theoretically Principled Trade-off between Robustness and Accuracy Hongyang R. Zhang Yaodong Yu Jiantao Jiao Eric Xing L. Ghaoui Michael I. Jordan 92 2,525 0 24 Jan 2019
On Lazy Training in Differentiable Programming Lénaïc Chizat Edouard Oyallon Francis R. Bach 78 823 0 19 Dec 2018
Feature Denoising for Improving Adversarial Robustness Cihang Xie Yuxin Wu Laurens van der Maaten Alan Yuille Kaiming He 69 907 0 09 Dec 2018
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness Robert Geirhos Patricia Rubisch Claudio Michaelis Matthias Bethge Felix Wichmann Wieland Brendel 65 2,647 0 29 Nov 2018
Excessive Invariance Causes Adversarial Vulnerability J. Jacobsen Jens Behrmann R. Zemel Matthias Bethge AAML 43 166 0 01 Nov 2018
Are adversarial examples inevitable? Ali Shafahi Wenjie Huang Christoph Studer Soheil Feizi Tom Goldstein SILM 44 282 0 06 Sep 2018
Implicit Bias of Gradient Descent on Linear Convolutional Networks Suriya Gunasekar Jason D. Lee Daniel Soudry Nathan Srebro MDE 40 408 0 01 Jun 2018
Adversarial examples from computational constraints Sébastien Bubeck Eric Price Ilya P. Razenshteyn AAML 80 230 0 25 May 2018
Deep learning generalizes because the parameter-function map is biased towards simple functions Guillermo Valle Pérez Chico Q. Camargo A. Louis MLT AI4CE 38 231 0 22 May 2018
Adversarially Robust Generalization Requires More Data Ludwig Schmidt Shibani Santurkar Dimitris Tsipras Kunal Talwar Aleksander Madry OOD AAML 109 786 0 30 Apr 2018
A Mean Field View of the Landscape of Two-Layers Neural Networks Song Mei Andrea Montanari Phan-Minh Nguyen MLT 61 855 0 18 Apr 2018
Annotation Artifacts in Natural Language Inference Data Suchin Gururangan Swabha Swayamdipta Omer Levy Roy Schwartz Samuel R. Bowman Noah A. Smith 78 1,167 0 06 Mar 2018
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples Anish Athalye Nicholas Carlini D. Wagner AAML 145 3,171 0 01 Feb 2018
MobileNetV2: Inverted Residuals and Linear Bottlenecks Mark Sandler Andrew G. Howard Menglong Zhu A. Zhmoginov Liang-Chieh Chen 103 19,124 0 13 Jan 2018
Size-Independent Sample Complexity of Neural Networks Noah Golowich Alexander Rakhlin Ohad Shamir 63 547 0 18 Dec 2017