Understanding deep learning requires rethinking generalization

10 November 2016

Benjamin Recht

Papers citing "Understanding deep learning requires rethinking generalization"

50 / 882 papers shown

Title
Noise Injection as a Probe of Deep Learning Dynamics Noam Levi I. Bloch M. Freytsis T. Volansky 40 2 0 24 Oct 2022
A PAC-Bayesian Generalization Bound for Equivariant Networks Arash Behboodi Gabriele Cesa Taco S. Cohen 56 17 0 24 Oct 2022
Revisiting Sparse Convolutional Model for Visual Recognition Xili Dai Mingyang Li Pengyuan Zhai Shengbang Tong Xingjian Gao Shao-Lun Huang Zhihui Zhu Chong You Y. Ma FAtt 35 27 0 24 Oct 2022
A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models Lijia Zhou Frederic Koehler Pragya Sur Danica J. Sutherland Nathan Srebro 83 9 0 21 Oct 2022
Optimisation & Generalisation in Networks of Neurons Jeremy Bernstein AI4CE 24 2 0 18 Oct 2022
Dimensionality of datasets in object detection networks Ajay Chawda A. Vierling Karsten Berns 3DPC 10 0 0 13 Oct 2022
SGD with Large Step Sizes Learns Sparse Features Maksym Andriushchenko Aditya Varre Loucas Pillaud-Vivien Nicolas Flammarion 45 56 0 11 Oct 2022
Block-wise Training of Residual Networks via the Minimizing Movement Scheme Skander Karkar Ibrahim Ayed Emmanuel de Bézenac Patrick Gallinari 30 1 0 03 Oct 2022
The Dynamic of Consensus in Deep Networks and the Identification of Noisy Labels Daniel Shwartz Uri Stern D. Weinshall NoLa 33 2 0 02 Oct 2022
On the Impossible Safety of Large AI Models El-Mahdi El-Mhamdi Sadegh Farhadkhani R. Guerraoui Nirupam Gupta L. Hoang Rafael Pinot Sébastien Rouault John Stephan 30 31 0 30 Sep 2022
Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel Sungyub Kim Si-hun Park Kyungsu Kim Eunho Yang BDL 29 4 0 30 Sep 2022
On the Robustness of Random Forest Against Untargeted Data Poisoning: An Ensemble-Based Approach M. Anisetti C. Ardagna Alessandro Balestrucci Nicola Bena Ernesto Damiani C. Yeun AAML OOD 29 10 0 28 Sep 2022
Why neural networks find simple solutions: the many regularizers of geometric complexity Benoit Dherin Michael Munn M. Rosca David Barrett 55 30 0 27 Sep 2022
Deep Double Descent via Smooth Interpolation Matteo Gamba Erik Englesson Marten Bjorkman Hossein Azizpour 63 10 0 21 Sep 2022
Deep Linear Networks can Benignly Overfit when Shallow Ones Do Niladri S. Chatterji Philip M. Long 23 8 0 19 Sep 2022
Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold Can Yaras Peng Wang Zhihui Zhu Laura Balzano Qing Qu 25 41 0 19 Sep 2022
Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty Thomas George Guillaume Lajoie A. Baratin 28 5 0 19 Sep 2022
Generalization Bounds for Deep Transfer Learning Using Majority Predictor Accuracy Cuong N.Nguyen L. Ho Vu C. Dinh Tal Hassner Cuong V.Nguyen 17 4 0 13 Sep 2022
Black-Box Audits for Group Distribution Shifts Marc Juárez Samuel Yeom Matt Fredrikson MLAU 24 4 0 08 Sep 2022
Data-Driven Target Localization Using Adaptive Radar Processing and Convolutional Neural Networks Shyam Venkatasubramanian S. Gogineni Bosung Kang Ali Pezeshki M. Rangaswamy Vahid Tarokh 30 3 0 07 Sep 2022
Generalisation under gradient descent via deterministic PAC-Bayes Eugenio Clerico Tyler Farghly George Deligiannidis Benjamin Guedj Arnaud Doucet 31 4 0 06 Sep 2022
Data Provenance via Differential Auditing Xin Mu Ming Pang Feida Zhu 11 1 0 04 Sep 2022
Instance-Dependent Noisy Label Learning via Graphical Modelling Arpit Garg Cuong C. Nguyen Rafael Felix Thanh-Toan Do G. Carneiro NoLa 34 27 0 02 Sep 2022
PanorAMS: Automatic Annotation for Detecting Objects in Urban Context Inske Groenen S. Rudinac M. Worring 21 4 0 30 Aug 2022
Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling Boshen Zhang Yuxi Li Yuanpeng Tu Jinlong Peng Yabiao Wang Cunlin Wu Yanghua Xiao Cairong Zhao NoLa 38 6 0 23 Aug 2022
Intersection of Parallels as an Early Stopping Criterion Ali Vardasbi Maarten de Rijke Mostafa Dehghani MoMe 38 5 0 19 Aug 2022
Do Quantum Circuit Born Machines Generalize? Kaitlin Gili Mohamed Hibat-Allah M. Mauri C. Ballance A. Perdomo-Ortiz 25 29 0 27 Jul 2022
Learning from Data with Noisy Labels Using Temporal Self-Ensemble Jun Ho Lee J. Baik Taebaek Hwang J. Choi NoLa 28 1 0 21 Jul 2022
Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting Neil Rohit Mallinar James B. Simon Amirhesam Abedsoltan Parthe Pandit M. Belkin Preetum Nakkiran 24 37 0 14 Jul 2022
PAC-Bayesian Domain Adaptation Bounds for Multiclass Learners Anthony Sicilia Katherine Atwell Malihe Alikhani Seong Jae Hwang BDL 51 9 0 12 Jul 2022
Utilizing Excess Resources in Training Neural Networks Amit Henig Raja Giryes 50 0 0 12 Jul 2022
Integral Probability Metrics PAC-Bayes Bounds Ron Amit Baruch Epstein Shay Moran Ron Meir 27 18 0 01 Jul 2022
ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy State Xinshao Wang Yang Hua Elyor Kodirov S. Mukherjee David A. Clifton N. Robertson 19 6 0 30 Jun 2022
Neural Networks can Learn Representations with Gradient Descent Alexandru Damian Jason D. Lee Mahdi Soltanolkotabi SSL MLT 19 114 0 30 Jun 2022
Semi-Supervised Generative Adversarial Network for Stress Detection Using Partially Labeled Physiological Data Nibraas Khan Nilanjan Sarkar 6 7 0 30 Jun 2022
On making optimal transport robust to all outliers Kilian Fatras OT 19 0 0 23 Jun 2022
Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation Loucas Pillaud-Vivien J. Reygner Nicolas Flammarion NoLa 33 31 0 20 Jun 2022
Gray Learning from Non-IID Data with Out-of-distribution Samples Zhilin Zhao LongBing Cao Changbao Wang OOD OODD 33 1 0 19 Jun 2022
Sparse Double Descent: Where Network Pruning Aggravates Overfitting Zhengqi He Zeke Xie Quanzhi Zhu Zengchang Qin 74 27 0 17 Jun 2022
Gradient-Based Adversarial and Out-of-Distribution Detection Jinsol Lee Mohit Prabhushankar Ghassan AlRegib UQCV 34 13 0 16 Jun 2022
Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep Learning Rui Liu Berrak Sisman Björn Schuller Guanglai Gao Haizhou Li 22 11 0 15 Jun 2022
Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction Kaifeng Lyu Zhiyuan Li Sanjeev Arora FAtt 40 69 0 14 Jun 2022
Towards Understanding Sharpness-Aware Minimization Maksym Andriushchenko Nicolas Flammarion AAML 32 133 0 13 Jun 2022
Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks Kaiqi Zhang Ming Yin Yu-Xiang Wang MQ 24 4 0 13 Jun 2022
NeuGuard: Lightweight Neuron-Guided Defense against Membership Inference Attacks Nuo Xu Binghui Wang Ran Ran Wujie Wen Parv Venkitasubramaniam AAML 20 5 0 11 Jun 2022
Adversarial Reprogramming Revisited Matthias Englert R. Lazic AAML 26 8 0 07 Jun 2022
Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm Aidan Good Jia-Huei Lin Hannah Sieg Mikey Ferguson Xin Yu Shandian Zhe J. Wieczorek Thiago Serra 37 11 0 07 Jun 2022
MSR: Making Self-supervised learning Robust to Aggressive Augmentations Ying-Long Bai Erkun Yang Zhaoqing Wang Yuxuan Du Bo Han Cheng Deng Dadong Wang Tongliang Liu SSL 25 3 0 04 Jun 2022
Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile Dong Chen Lingfei Wu Siliang Tang Xiao Yun Bo Long Yueting Zhuang VLM NoLa 25 9 0 04 Jun 2022
Regularization-wise double descent: Why it occurs and how to eliminate it Fatih Yilmaz Reinhard Heckel 27 11 0 03 Jun 2022