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 / 942 papers shown

Title
$On the robustness of the minimum $\ell_2$ interpolator$ On the robustness of the minimum $\ell_2$ interpolator Geoffrey Chinot M. Lerasle 132 10 0 12 Mar 2020
Getting Better from Worse: Augmented Bagging and a Cautionary Tale of Variable ImportanceJournal of machine learning research (JMLR), 2020 L. Mentch Siyu Zhou 179 18 0 07 Mar 2020
Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited Wesley J. Maddox Gregory W. Benton A. Wilson 243 66 0 04 Mar 2020
Optimal Regularization Can Mitigate Double DescentInternational Conference on Learning Representations (ICLR), 2020 Preetum Nakkiran Prayaag Venkat Sham Kakade Tengyu Ma 223 146 0 04 Mar 2020
Double Trouble in Double Descent : Bias and Variance(s) in the Lazy RegimeInternational Conference on Machine Learning (ICML), 2020 Stéphane dÁscoli Maria Refinetti Giulio Biroli Florent Krzakala 367 158 0 02 Mar 2020
Loss landscapes and optimization in over-parameterized non-linear systems and neural networksApplied and Computational Harmonic Analysis (ACHA), 2020 Chaoyue Liu Libin Zhu M. Belkin ODL 304 301 0 29 Feb 2020
Disentangling Adaptive Gradient Methods from Learning Rates Naman Agarwal Rohan Anil Elad Hazan Tomer Koren Cyril Zhang 227 41 0 26 Feb 2020
Overfitting in adversarially robust deep learningInternational Conference on Machine Learning (ICML), 2020 Leslie Rice Eric Wong Zico Kolter 509 884 0 26 Feb 2020
The role of regularization in classification of high-dimensional noisy Gaussian mixtureInternational Conference on Machine Learning (ICML), 2020 Francesca Mignacco Florent Krzakala Yue M. Lu Lenka Zdeborová 191 96 0 26 Feb 2020
Rethinking Bias-Variance Trade-off for Generalization of Neural NetworksInternational Conference on Machine Learning (ICML), 2020 Zitong Yang Yaodong Yu Chong You Jacob Steinhardt Yi-An Ma 306 210 0 26 Feb 2020
The Curious Case of Adversarially Robust Models: More Data Can Help, Double Descend, or Hurt GeneralizationConference on Uncertainty in Artificial Intelligence (UAI), 2020 Yifei Min Lin Chen Amin Karbasi AAML 238 72 0 25 Feb 2020
Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based OptimizationInternational Conference on Learning Representations (ICLR), 2020 S. Chatterjee ODL OOD 216 57 0 25 Feb 2020
Subspace Fitting Meets Regression: The Effects of Supervision and Orthonormality Constraints on Double Descent of Generalization ErrorsInternational Conference on Machine Learning (ICML), 2020 Yehuda Dar Paul Mayer Lorenzo Luzi Richard G. Baraniuk 209 17 0 25 Feb 2020
Self-Adaptive Training: beyond Empirical Risk MinimizationNeural Information Processing Systems (NeurIPS), 2020 Lang Huang Chaoning Zhang Hongyang R. Zhang NoLa 303 226 0 24 Feb 2020
Generalisation error in learning with random features and the hidden manifold modelInternational Conference on Machine Learning (ICML), 2020 Federica Gerace Bruno Loureiro Florent Krzakala M. Mézard Lenka Zdeborová 259 179 0 21 Feb 2020
Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nyström method Michal Derezinski Rajiv Khanna Michael W. Mahoney 269 10 0 21 Feb 2020
Bayesian Deep Learning and a Probabilistic Perspective of GeneralizationNeural Information Processing Systems (NeurIPS), 2020 A. Wilson Pavel Izmailov UQCV BDL OOD 599 730 0 20 Feb 2020
Do We Need Zero Training Loss After Achieving Zero Training Error?International Conference on Machine Learning (ICML), 2020 Takashi Ishida Ikko Yamane Tomoya Sakai Gang Niu Masashi Sugiyama AI4CE 171 154 0 20 Feb 2020
Implicit Regularization of Random Feature ModelsInternational Conference on Machine Learning (ICML), 2020 Arthur Jacot Berfin Simsek Francesco Spadaro Clément Hongler Franck Gabriel 265 84 0 19 Feb 2020
Predicting trends in the quality of state-of-the-art neural networks without access to training or testing dataNature Communications (Nat Commun), 2020 Charles H. Martin Tongsu Peng Peng Michael W. Mahoney 332 132 0 17 Feb 2020
Hold me tight! Influence of discriminative features on deep network boundariesNeural Information Processing Systems (NeurIPS), 2020 Guillermo Ortiz-Jiménez Apostolos Modas Seyed-Mohsen Moosavi-Dezfooli P. Frossard AAML 189 51 0 15 Feb 2020
Estimating Uncertainty Intervals from Collaborating NetworksJournal of machine learning research (JMLR), 2020 Tianhui Zhou Yitong Li Yuan Wu David Carlson UQCV 340 17 0 12 Feb 2020
Self-explaining AI as an alternative to interpretable AIArtificial General Intelligence (AGI), 2020 Daniel C. Elton 396 62 0 12 Feb 2020
Sparse Recovery With Non-Linear Fourier FeaturesIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020 Ayça Özçelikkale 133 5 0 12 Feb 2020
Think Global, Act Local: Relating DNN generalisation and node-level SNR Paul Norridge 79 1 0 11 Feb 2020
Asymptotic errors for convex penalized linear regression beyond Gaussian matrices Cédric Gerbelot A. Abbara Florent Krzakala 134 17 0 11 Feb 2020
Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural NetworksInternational Conference on Machine Learning (ICML), 2020 Blake Bordelon Abdulkadir Canatar Cengiz Pehlevan 699 230 0 07 Feb 2020
Interpolating Predictors in High-Dimensional Factor Regression F. Bunea Seth Strimas-Mackey M. Wegkamp 259 12 0 06 Feb 2020
Global Convergence of Frank Wolfe on One Hidden Layer Networks Alexandre d’Aspremont Mert Pilanci 149 4 0 06 Feb 2020
Semi-Exact Control Functionals From Sard's MethodBiometrika (Biometrika), 2020 Leah F. South Toni Karvonen Christopher Nemeth Mark Girolami Chris J. Oates 205 18 0 31 Jan 2020
Analytic Study of Double Descent in Binary Classification: The Impact of LossInternational Symposium on Information Theory (ISIT), 2020 Ganesh Ramachandra Kini Christos Thrampoulidis 162 55 0 30 Jan 2020
Convergence Guarantees for Gaussian Process Means With Misspecified Likelihoods and SmoothnessJournal of machine learning research (JMLR), 2020 George Wynne F. Briol Mark Girolami 338 68 0 29 Jan 2020
Big-Data Science in Porous Materials: Materials Genomics and Machine LearningChemical Reviews (Chem. Rev.), 2020 Kevin Maik Jablonka D. Ongari S. M. Moosavi B. Smit AI4CE 235 402 0 18 Jan 2020
On Interpretability of Artificial Neural Networks: A SurveyIEEE Transactions on Radiation and Plasma Medical Sciences (TRPMS), 2020 Fenglei Fan Jinjun Xiong Mengzhou Li Ge Wang AAML AI4CE 373 370 0 08 Jan 2020
From Learning to Meta-Learning: Reduced Training Overhead and Complexity for Communication Systems6G Wireless Summit (6G Summit), 2020 Osvaldo Simeone Sangwoo Park Joonhyuk Kang AI4CE 244 63 0 05 Jan 2020
Relative Flatness and GeneralizationNeural Information Processing Systems (NeurIPS), 2020 Henning Petzka Michael Kamp Linara Adilova C. Sminchisescu Mario Boley 302 89 0 03 Jan 2020
Implicit Regularization and Momentum Algorithms in Nonlinearly Parameterized Adaptive Control and PredictionNeural Computation (Neural Comput.), 2019 Nicholas M. Boffi Jean-Jacques E. Slotine 227 43 0 31 Dec 2019
Machine Learning from a Continuous ViewpointScience China Mathematics (Sci. China Math.), 2019 E. Weinan Chao Ma Lei Wu 254 110 0 30 Dec 2019
Optimization for deep learning: theory and algorithms Tian Ding ODL 267 177 0 19 Dec 2019
On the Bias-Variance Tradeoff: Textbooks Need an Update Brady Neal 91 20 0 17 Dec 2019
The Generalization Error of the Minimum-norm Solutions for Over-parameterized Neural Networks E. Weinan Chao Ma Lei Wu 182 14 0 15 Dec 2019
Double descent in the condition number T. Poggio Gil Kur Andy Banburski 164 28 0 12 Dec 2019
Mean-Field Neural ODEs via Relaxed Optimal Control Jean-François Jabir D. vSivska Lukasz Szpruch MLT 223 37 0 11 Dec 2019
Exact expressions for double descent and implicit regularization via surrogate random designNeural Information Processing Systems (NeurIPS), 2019 Michal Derezinski Feynman T. Liang Michael W. Mahoney 289 79 0 10 Dec 2019
In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictorsInternational Conference on Machine Learning (ICML), 2019 Jeffrey Negrea Gintare Karolina Dziugaite Daniel M. Roy AI4CE 266 66 0 09 Dec 2019
Deep Double Descent: Where Bigger Models and More Data HurtInternational Conference on Learning Representations (ICLR), 2019 Preetum Nakkiran Gal Kaplun Yamini Bansal Tristan Yang Boaz Barak Ilya Sutskever 314 1,045 0 04 Dec 2019
Extreme Learning Machine design for dealing with unrepresentative features Nicolás Nieto F. Ibarrola Victoria Peterson H. Rufiner Rubén D. Spies 74 3 0 04 Dec 2019
Long Distance Relationships without Time Travel: Boosting the Performance of a Sparse Predictive Autoencoder in Sequence ModelingIAPR International Workshop on Artificial Neural Networks in Pattern Recognition (ANNPR), 2019 J. Gordon D. Rawlinson Subutai Ahmad 111 5 0 02 Dec 2019
A Random Matrix Perspective on Mixtures of Nonlinearities for Deep LearningInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2019 Ben Adlam J. Levinson Jeffrey Pennington 165 26 0 02 Dec 2019
How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?International Conference on Learning Representations (ICLR), 2019 Zixiang Chen Yuan Cao Difan Zou Quanquan Gu 305 129 0 27 Nov 2019