v1v2 (latest)

Reconciling modern machine learning practice and the bias-variance trade-off

28 December 2018

Papers citing "Reconciling modern machine learning practice and the bias-variance trade-off"

50 / 943 papers shown

Title
On Implicit Bias in Overparameterized Bilevel OptimizationInternational Conference on Machine Learning (ICML), 2022 Paul Vicol Jon Lorraine Fabian Pedregosa David Duvenaud Roger C. Grosse AI4CE 242 45 0 28 Dec 2022
Homophily modulates double descent generalization in graph convolution networksProceedings of the National Academy of Sciences of the United States of America (PNAS), 2022 Chengzhi Shi Liming Pan Hong Hu Ivan Dokmanić 373 12 0 26 Dec 2022
The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for Deep Quantum Machine LearningIEEE Transactions on Quantum Engineering (IEEE Trans. Quantum Eng.), 2022 Massimiliano Incudini Michele Grossi Antonio Mandarino S. Vallecorsa Alessandra Di Pierro David Windridge 262 14 0 22 Dec 2022
Reproducible scaling laws for contrastive language-image learningComputer Vision and Pattern Recognition (CVPR), 2022 Mehdi Cherti Romain Beaumont Ross Wightman Mitchell Wortsman Gabriel Ilharco Cade Gordon Christoph Schuhmann Ludwig Schmidt J. Jitsev VLM CLIP 469 1,138 0 14 Dec 2022
Gradient flow in the gaussian covariate model: exact solution of learning curves and multiple descent structures Antione Bodin N. Macris 202 4 0 13 Dec 2022
Reliable extrapolation of deep neural operators informed by physics or sparse observationsSocial Science Research Network (SSRN), 2022 Min Zhu Handi Zhang Anran Jiao George Karniadakis Lu Lu 247 127 0 13 Dec 2022
$Tight bounds for maximum $\ell_1$-margin classifiers$ Tight bounds for maximum $\ell_1$ -margin classifiers Stefan Stojanovic Konstantin Donhauser Fanny Yang 277 0 0 07 Dec 2022
Improved Convergence Guarantees for Shallow Neural Networks A. Razborov ODL 205 1 0 05 Dec 2022
High Dimensional Binary Classification under Label Shift: Phase Transition and RegularizationSampling Theory, Signal Processing, and Data Analysis (SampTA), 2022 Jiahui Cheng Minshuo Chen Hao Liu Tuo Zhao Wenjing Liao 301 1 0 01 Dec 2022
Regularization Trade-offs with Fake FeaturesEuropean Signal Processing Conference (EUSIPCO), 2022 Martin Hellkvist Ayça Özçelikkale Anders Ahlén 341 0 0 01 Dec 2022
Task Discovery: Finding the Tasks that Neural Networks Generalize onNeural Information Processing Systems (NeurIPS), 2022 Andrei Atanov Andrei Filatov Teresa Yeo Ajay Sohmshetty Amir Zamir OOD 370 11 0 01 Dec 2022
Nonlinear Advantage: Trained Networks Might Not Be As Complex as You ThinkInternational Conference on Machine Learning (ICML), 2022 Christian H. X. Ali Mehmeti-Göpel Jan Disselhoff 175 6 0 30 Nov 2022
Why Neural Networks WorkIntelligent Systems with Applications (ISA), 2022 Sayan Mukherjee Bernardo A. Huberman 112 2 0 26 Nov 2022
The Vanishing Decision Boundary Complexity and the Strong First Component Hengshuai Yao UQCV 161 0 0 25 Nov 2022
The smooth output assumption, and why deep networks are better than wide ones Luis Sa-Couto J. M. Ramos Andreas Wichert 103 0 0 25 Nov 2022
A Survey of Learning Curves with Bad Behavior: or How More Data Need Not Lead to Better Performance Marco Loog T. Viering 184 2 0 25 Nov 2022
Frozen Overparameterization: A Double Descent Perspective on Transfer Learning of Deep Neural Networks Yehuda Dar Lorenzo Luzi Richard G. Baraniuk AI4CE 181 2 0 20 Nov 2022
Understanding the double descent curve in Machine Learning Luis Sa-Couto J. M. Ramos Miguel Almeida Andreas Wichert 127 3 0 18 Nov 2022
Emergence of Concepts in DNNs? Tim Räz 61 0 0 11 Nov 2022
Do highly over-parameterized neural networks generalize since bad solutions are rare?IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022 Julius Martinetz T. Martinetz 389 1 0 07 Nov 2022
Reward-Predictive Clustering Lucas Lehnert M. Frank Michael L. Littman OffRL 179 0 0 07 Nov 2022
Instance-Dependent Generalization Bounds via Optimal TransportJournal of machine learning research (JMLR), 2022 Songyan Hou Parnian Kassraie Anastasis Kratsios Andreas Krause Jonas Rothfuss 479 12 0 02 Nov 2022
Transfer Learning with Kernel MethodsNature Communications (Nat Commun), 2022 Adityanarayanan Radhakrishnan Max Ruiz Luyten Neha Prasad Caroline Uhler 146 28 0 01 Nov 2022
Globally Gated Deep Linear NetworksNeural Information Processing Systems (NeurIPS), 2022 Qianyi Li H. Sompolinsky AI4CE 219 15 0 31 Oct 2022
A Law of Data Separation in Deep LearningProceedings of the National Academy of Sciences of the United States of America (PNAS), 2022 Hangfeng He Weijie J. Su OOD 300 49 0 31 Oct 2022
A Solvable Model of Neural Scaling Laws A. Maloney Daniel A. Roberts J. Sully 225 77 0 30 Oct 2022
Grokking phase transitions in learning local rules with gradient descentJournal of machine learning research (JMLR), 2022 Bojan Žunkovič E. Ilievski 262 22 0 26 Oct 2022
Learning Ability of Interpolating Deep Convolutional Neural NetworksSocial Science Research Network (SSRN), 2022 Tiancong Zhou X. Huo AI4CE 173 14 0 25 Oct 2022
Deep Neural Networks as the Semi-classical Limit of Topological Quantum Neural Networks: The problem of generalisation A. Marcianò De-Wei Chen Filippo Fabrocini C. Fields M. Lulli Emanuele Zappala GNN 106 6 0 25 Oct 2022
Pruning's Effect on Generalization Through the Lens of Training and RegularizationNeural Information Processing Systems (NeurIPS), 2022 Tian Jin Michael Carbin Daniel M. Roy Jonathan Frankle Gintare Karolina Dziugaite 212 33 0 25 Oct 2022
On double-descent in uncertainty quantification in overparametrized modelsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 Lucas Clarté Bruno Loureiro Florent Krzakala Lenka Zdeborová UQCV 442 14 0 23 Oct 2022
Monotonicity and Double Descent in Uncertainty Estimation with Gaussian ProcessesInternational Conference on Machine Learning (ICML), 2022 Liam Hodgkinson Christopher van der Heide Fred Roosta Michael W. Mahoney UQCV 245 7 0 14 Oct 2022
Identification of quantum entanglement with Siamese convolutional neural networks and semi-supervised learningPhysical Review Applied (Phys. Rev. Appl.), 2022 J. Pawłowski Mateusz Krawczyk 243 6 0 13 Oct 2022
The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspectiveJournal of machine learning research (JMLR), 2022 Chi-Heng Lin Chiraag Kaushik Eva L. Dyer Vidya Muthukumar 356 41 0 10 Oct 2022
Second-order regression models exhibit progressive sharpening to the edge of stabilityInternational Conference on Machine Learning (ICML), 2022 Atish Agarwala Fabian Pedregosa Jeffrey Pennington 240 32 0 10 Oct 2022
Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals Rohin Shah Vikrant Varma Ramana Kumar Mary Phuong Victoria Krakovna J. Uesato Zachary Kenton 415 102 0 04 Oct 2022
Block-wise Training of Residual Networks via the Minimizing Movement Scheme Skander Karkar Ibrahim Ayed Emmanuel de Bézenac Patrick Gallinari 206 1 0 03 Oct 2022
Ten Years after ImageNet: A 360° Perspective on AI Sanjay Chawla Preslav Nakov Ahmed Ali Wendy Hall Issa M. Khalil Xiaosong Ma Husrev Taha Sencar Ingmar Weber Michael Wooldridge Tingyue Yu 79 0 0 01 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 333 37 0 30 Sep 2022
Why neural networks find simple solutions: the many regularizers of geometric complexityNeural Information Processing Systems (NeurIPS), 2022 Benoit Dherin Michael Munn M. Rosca David Barrett 324 42 0 27 Sep 2022
In-context Learning and Induction Heads Catherine Olsson Nelson Elhage Neel Nanda Nicholas Joseph Nova Dassarma ... Tom B. Brown Jack Clark Jared Kaplan Sam McCandlish C. Olah 582 692 0 24 Sep 2022
Deep Double Descent via Smooth Interpolation Matteo Gamba Erik Englesson Mårten Björkman Hossein Azizpour 599 12 0 21 Sep 2022
Deep Linear Networks can Benignly Overfit when Shallow Ones DoJournal of machine learning research (JMLR), 2022 Niladri S. Chatterji Philip M. Long 215 11 0 19 Sep 2022
Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty Thomas George Guillaume Lajoie A. Baratin 175 7 0 19 Sep 2022
Importance Tempering: Group Robustness for Overparameterized Models Yiping Lu Wenlong Ji Zachary Izzo Lexing Ying 247 7 0 19 Sep 2022
Random Fourier Features for Asymmetric KernelsMachine-mediated learning (ML), 2022 Ming-qian He Fan He Fanghui Liu Xiaolin Huang 182 5 0 18 Sep 2022
Generalization in Neural Networks: A Broad SurveyNeurocomputing (Neurocomputing), 2022 Chris Rohlfs OOD AI4CE 261 18 0 04 Sep 2022
Towards Understanding the Overfitting Phenomenon of Deep Click-Through Rate Prediction ModelsInternational Conference on Information and Knowledge Management (CIKM), 2022 Zhaorui Zhang Xiang-Rong Sheng Yujing Zhang Biye Jiang Shuguang Han Hongbo Deng Bo Zheng CML 187 47 0 04 Sep 2022
Revisiting Outer Optimization in Adversarial TrainingEuropean Conference on Computer Vision (ECCV), 2022 Ali Dabouei Fariborz Taherkhani Sobhan Soleymani Nasser M. Nasrabadi AAML 235 6 0 02 Sep 2022
Information FOMO: The unhealthy fear of missing out on information. A method for removing misleading data for healthier models Ethan Pickering T. Sapsis 263 7 0 27 Aug 2022