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 Inherent Regularization Effects of Noise Injection During TrainingInternational Conference on Machine Learning (ICML), 2021 Oussama Dhifallah Yue M. Lu 125 33 0 15 Feb 2021
Double-descent curves in neural networks: a new perspective using Gaussian processesAAAI Conference on Artificial Intelligence (AAAI), 2021 Ouns El Harzli Bernardo Cuenca Grau Guillermo Valle Pérez A. Louis 366 6 0 14 Feb 2021
Distilling Double Descent Andrew Cotter A. Menon Harikrishna Narasimhan A. S. Rawat Sashank J. Reddi Yichen Zhou 139 7 0 13 Feb 2021
Learning Curve Theory Marcus Hutter 333 77 0 08 Feb 2021
Last iterate convergence of SGD for Least-Squares in the Interpolation regimeNeural Information Processing Systems (NeurIPS), 2021 Aditya Varre Loucas Pillaud-Vivien Nicolas Flammarion 164 43 0 05 Feb 2021
A Deeper Look into Convolutions via Eigenvalue-based Pruning Ilke Çugu Emre Akbas FAtt 115 2 0 04 Feb 2021
Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff PerspectiveInternational Conference on Learning Representations (ICLR), 2021 Helong Zhou Liangchen Song Jiajie Chen Ye Zhou Guoli Wang Junsong Yuan Qian Zhang 339 199 0 01 Feb 2021
Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced TrainingProceedings of the National Academy of Sciences of the United States of America (PNAS), 2021 Cong Fang Hangfeng He Qi Long Weijie J. Su FAtt 404 202 0 29 Jan 2021
A Statistician Teaches Deep LearningJournal of Statistical Theory and Practice (JSTP), 2021 G. Babu David L. Banks Hyunsoo Cho David Han Hailin Sang Shouyi Wang 207 2 0 29 Jan 2021
Generalization error of random features and kernel methods: hypercontractivity and kernel matrix concentrationApplied and Computational Harmonic Analysis (ACHA), 2021 Song Mei Theodor Misiakiewicz Andrea Montanari 210 123 0 26 Jan 2021
Deep Learning Generalization and the Convex Hull of Training Sets Roozbeh Yousefzadeh 124 20 0 25 Jan 2021
Linear Regression with Distributed Learning: A Generalization Error PerspectiveIEEE Transactions on Signal Processing (IEEE TSP), 2021 Martin Hellkvist Ayça Özçelikkale Anders Ahlén FedML 251 10 0 22 Jan 2021
Self-Adaptive Training: Bridging Supervised and Self-Supervised LearningIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 Lang Huang Chaoning Zhang Hongyang R. Zhang SSL 248 30 0 21 Jan 2021
Implicit Bias of Linear RNNsInternational Conference on Machine Learning (ICML), 2021 M Motavali Emami Mojtaba Sahraee-Ardakan Parthe Pandit S. Rangan A. Fletcher 129 13 0 19 Jan 2021
Phases of learning dynamics in artificial neural networks: with or without mislabeled data Yu Feng Y. Tu 100 2 0 16 Jan 2021
Fitting very flexible models: Linear regression with large numbers of parametersPublications of the Astronomical Society of the Pacific (PASP), 2021 D. Hogg Soledad Villar 168 7 0 15 Jan 2021
The data synergy effects of time-series deep learning models in hydrologyWater Resources Research (WRR), 2021 K. Fang Daniel Kifer K. Lawson D. Feng Chaopeng Shen AI4CE 285 103 0 06 Jan 2021
A unifying approach on bias and variance analysis for classification Cemre Zor T. Windeatt 23 0 0 05 Jan 2021
Perspective: A Phase Diagram for Deep Learning unifying Jamming, Feature Learning and Lazy Training Mario Geiger Leonardo Petrini Matthieu Wyart DRL 157 11 0 30 Dec 2020
Analysis of the Scalability of a Deep-Learning Network for Steganography "Into the Wild" Hugo Ruiz Marc Chaumont Mehdi Yedroudj A. Amara Frédéric Comby Gérard Subsol 129 9 0 29 Dec 2020
Data augmentation and image understanding Alex Hernandez-Garcia 134 6 0 28 Dec 2020
Applying Deutsch's concept of good explanations to artificial intelligence and neuroscience -- an initial explorationCognitive Systems Research (CSR), 2020 Daniel C. Elton 191 4 0 16 Dec 2020
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural NetworksAAAI Conference on Artificial Intelligence (AAAI), 2020 Xiangyu Chang Yingcong Li Samet Oymak Christos Thrampoulidis 248 58 0 16 Dec 2020
A case for new neural network smoothness constraints Mihaela Rosca T. Weber Arthur Gretton S. Mohamed AAML 291 59 0 14 Dec 2020
Avoiding The Double Descent Phenomenon of Random Feature Models Using Hybrid Regularization Kelvin K. Kan J. Nagy Lars Ruthotto AI4CE 113 6 0 11 Dec 2020
Beyond Occam's Razor in System Identification: Double-Descent when Modeling DynamicsIFAC-PapersOnLine (IFAC-PapersOnLine), 2020 Antônio H. Ribeiro J. Hendriks A. Wills Thomas B. Schon 95 8 0 11 Dec 2020
Generalization bounds for deep learning Guillermo Valle Pérez A. Louis BDL 231 48 0 07 Dec 2020
Statistical Mechanics of Deep Linear Neural Networks: The Back-Propagating Kernel Renormalization Qianyi Li H. Sompolinsky 374 84 0 07 Dec 2020
Model Compression Using Optimal Transport Suhas Lohit Michael J. Jones 201 9 0 07 Dec 2020
Understanding Interpretability by generalized distillation in Supervised Classification Adit Agarwal Dr. K.K. Shukla Arjan Kuijper Anirban Mukhopadhyay FaML FAtt 128 0 0 05 Dec 2020
Rethinking supervised learning: insights from biological learning and from calling it by its name Alex Hernandez-Garcia SSL 147 0 0 04 Dec 2020
On the robustness of minimum norm interpolators and regularized empirical risk minimizersAnnals of Statistics (Ann. Stat.), 2020 Geoffrey Chinot Matthias Löffler Sara van de Geer 284 22 0 01 Dec 2020
Scaling Down Deep Learning with MNIST-1DInternational Conference on Machine Learning (ICML), 2020 S. Greydanus Dmitry Kobak 252 24 0 29 Nov 2020
Dimensionality reduction, regularization, and generalization in overparameterized regressionsSIAM Journal on Mathematics of Data Science (SIMODS), 2020 Ningyuan Huang D. Hogg Soledad Villar 204 18 0 23 Nov 2020
Deep Empirical Risk Minimization in finance: looking into the futureMathematical Finance (Math. Finance), 2020 A. M. Reppen H. Soner 202 21 0 18 Nov 2020
Topological properties of basins of attraction and expressiveness of width bounded neural networks H. Beise S. Cruz 277 0 0 10 Nov 2020
Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification Agus Sudjianto William Knauth Rahul Singh Zebin Yang Aijun Zhang FAtt 200 50 0 08 Nov 2020
Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition Ben Adlam Jeffrey Pennington UD 223 102 0 04 Nov 2020
Instance based Generalization in Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2020 Martín Bertrán Natalia Martínez Mariano Phielipp Guillermo Sapiro OffRL 222 19 0 02 Nov 2020
The Performance Analysis of Generalized Margin Maximizer (GMM) on Separable DataInternational Conference on Machine Learning (ICML), 2020 Fariborz Salehi Ehsan Abbasi B. Hassibi 131 19 0 29 Oct 2020
A Bayesian Perspective on Training Speed and Model SelectionNeural Information Processing Systems (NeurIPS), 2020 Clare Lyle Lisa Schut Binxin Ru Y. Gal Mark van der Wilk 180 24 0 27 Oct 2020
Are wider nets better given the same number of parameters?International Conference on Learning Representations (ICLR), 2020 A. Golubeva Behnam Neyshabur Guy Gur-Ari 202 46 0 27 Oct 2020
Memorizing without overfitting: Bias, variance, and interpolation in over-parameterized modelsPhysical Review Research (PRResearch), 2020 J. Rocks Pankaj Mehta 381 54 0 26 Oct 2020
Provable Memorization via Deep Neural Networks using Sub-linear ParametersAnnual Conference Computational Learning Theory (COLT), 2020 Sejun Park Jaeho Lee Chulhee Yun Jinwoo Shin FedML MDE 165 43 0 26 Oct 2020
Unified Gradient Reweighting for Model Biasing with Applications to Source SeparationIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020 Efthymios Tzinis Dimitrios Bralios Paris Smaragdis 240 1 0 25 Oct 2020
Train simultaneously, generalize better: Stability of gradient-based minimax learnersInternational Conference on Machine Learning (ICML), 2020 Farzan Farnia Asuman Ozdaglar 163 53 0 23 Oct 2020
Fast and Smooth Interpolation on Wasserstein Space Sinho Chewi Julien Clancy Thibaut Le Gouic Philippe Rigollet George Stepaniants Austin J. Stromme 149 32 0 22 Oct 2020
Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers Fan Yang Hongyang R. Zhang Sen Wu Christopher Ré Weijie J. Su 454 20 0 22 Oct 2020
Precise Statistical Analysis of Classification Accuracies for Adversarial Training Adel Javanmard Mahdi Soltanolkotabi AAML 357 66 0 21 Oct 2020
Increasing Depth Leads to U-Shaped Test Risk in Over-parameterized Convolutional Networks Eshaan Nichani Adityanarayanan Radhakrishnan Caroline Uhler 263 9 0 19 Oct 2020