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
Multiple Descent in the Multiple Random Feature ModelJournal of machine learning research (JMLR), 2022 Xuran Meng Jianfeng Yao Yuan Cao 204 9 0 21 Aug 2022
Intersection of Parallels as an Early Stopping CriterionInternational Conference on Information and Knowledge Management (CIKM), 2022 Ali Vardasbi Maarten de Rijke Mostafa Dehghani MoMe 123 7 0 19 Aug 2022
Investigating the Impact of Model Width and Density on Generalization in Presence of Label NoiseConference on Uncertainty in Artificial Intelligence (UAI), 2022 Yihao Xue Kyle Whitecross Baharan Mirzasoleiman NoLa 353 2 0 17 Aug 2022
Neural Set Function Extensions: Learning with Discrete Functions in High DimensionsNeural Information Processing Systems (NeurIPS), 2022 Nikolaos Karalias Joshua Robinson Andreas Loukas Stefanie Jegelka 325 11 0 08 Aug 2022
Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimalityNeural Information Processing Systems (NeurIPS), 2022 Wave Ngampruetikorn David J. Schwab 132 10 0 08 Aug 2022
What Can Transformers Learn In-Context? A Case Study of Simple Function ClassesNeural Information Processing Systems (NeurIPS), 2022 Shivam Garg Dimitris Tsipras Abigail Z. Jacobs Gregory Valiant 601 663 0 01 Aug 2022
ORFit: One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-SquaresIEEE Conference on Decision and Control (CDC), 2022 Youngjae Min Kwangjun Ahn Navid Azizan 268 23 0 28 Jul 2022
The BUTTER Zone: An Empirical Study of Training Dynamics in Fully Connected Neural Networks Charles Edison Tripp J. Perr-Sauer L. Hayne M. Lunacek Jamil Gafur AI4CE 256 1 0 25 Jul 2022
A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear PredictorsSIAM Journal on Mathematics of Data Science (SIMODS), 2022 Nikhil Ghosh M. Belkin 290 7 0 23 Jul 2022
Bounding generalization error with input compression: An empirical study with infinite-width networks A. Galloway A. Golubeva Mahmoud Salem Mihai Nica Yani Andrew Ioannou Graham W. Taylor MLT AI4CE 183 5 0 19 Jul 2022
Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting Neil Rohit Mallinar James B. Simon Amirhesam Abedsoltan Parthe Pandit M. Belkin Preetum Nakkiran 308 39 0 14 Jul 2022
On the Principles of Parsimony and Self-Consistency for the Emergence of IntelligenceFrontiers of Information Technology & Electronic Engineering (FITEE), 2022 Yi Ma Doris Y. Tsao H. Shum 224 87 0 11 Jul 2022
Towards Multimodal Vision-Language Models Generating Non-Generic TextICON (ICON), 2022 Wes Robbins Zanyar Zohourianshahzadi Jugal Kalita 156 1 0 09 Jul 2022
Target alignment in truncated kernel ridge regressionNeural Information Processing Systems (NeurIPS), 2022 Arash A. Amini R. Baumgartner Dai Feng 190 4 0 28 Jun 2022
Benign overfitting and adaptive nonparametric regressionProbability theory and related fields (PTRF), 2022 J. Chhor Suzanne Sigalla Alexandre B. Tsybakov 132 3 0 27 Jun 2022
On how to avoid exacerbating spurious correlations when models are overparameterizedInternational Symposium on Information Theory (ISIT), 2022 Tina Behnia Ke Wang Christos Thrampoulidis 204 3 0 25 Jun 2022
Ensembling over Classifiers: a Bias-Variance Perspective Neha Gupta Jamie Smith Ben Adlam Zelda E. Mariet FedML UQCV FaML 138 8 0 21 Jun 2022
Disentangling Model Multiplicity in Deep Learning Ari Heljakka Martin Trapp Arno Solin Arno Solin 159 6 0 17 Jun 2022
Tensor-on-Tensor Regression: Riemannian Optimization, Over-parameterization, Statistical-computational Gap, and Their InterplayAnnals of Statistics (Ann. Stat.), 2022 Yuetian Luo Anru R. Zhang 285 25 0 17 Jun 2022
Fast Finite Width Neural Tangent KernelInternational Conference on Machine Learning (ICML), 2022 Roman Novak Jascha Narain Sohl-Dickstein S. Schoenholz AAML 184 71 0 17 Jun 2022
Sparse Double Descent: Where Network Pruning Aggravates OverfittingInternational Conference on Machine Learning (ICML), 2022 Zhengqi He Zeke Xie Quanzhi Zhu Zengchang Qin 226 33 0 17 Jun 2022
Analysis of function approximation and stability of general DNNs in directed acyclic graphs using un-rectifying analysis Wonjun Hwang Shih-Shuo Tung 140 4 0 13 Jun 2022
Data-Efficient Brain Connectome Analysis via Multi-Task Meta-LearningKnowledge Discovery and Data Mining (KDD), 2022 Yi Yang Yanqiao Zhu Hejie Cui Xuan Kan Lifang He Ying Guo Carl Yang 137 34 0 09 Jun 2022
Trajectory-dependent Generalization Bounds for Deep Neural Networks via Fractional Brownian Motion Chengli Tan Jiang Zhang Junmin Liu 198 1 0 09 Jun 2022
Neural Collapse: A Review on Modelling Principles and Generalization Vignesh Kothapalli 359 101 0 08 Jun 2022
Understanding Deep Learning via Decision BoundaryIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022 Shiye Lei Fengxiang He Yancheng Yuan Dacheng Tao 190 23 0 03 Jun 2022
Generalization for multiclass classification with overparameterized linear modelsNeural Information Processing Systems (NeurIPS), 2022 Vignesh Subramanian Rahul Arya A. Sahai AI4CE 164 12 0 03 Jun 2022
Regularization-wise double descent: Why it occurs and how to eliminate itInternational Symposium on Information Theory (ISIT), 2022 Fatih Yilmaz Reinhard Heckel 175 11 0 03 Jun 2022
Analysis of Catastrophic Forgetting for Random Orthogonal Transformation Tasks in the Overparameterized RegimeInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 Daniel Goldfarb Paul Hand CLL 144 18 0 01 Jun 2022
Benign Overfitting in Classification: Provably Counter Label Noise with Larger ModelsInternational Conference on Learning Representations (ICLR), 2022 Kaiyue Wen Jiaye Teng J.N. Zhang NoLa 125 5 0 01 Jun 2022
Optimal Activation Functions for the Random Features Regression ModelInternational Conference on Learning Representations (ICLR), 2022 Jianxin Wang José Bento 235 4 0 31 May 2022
VC Theoretical Explanation of Double Descent Eng Hock Lee V. Cherkassky 138 4 0 31 May 2022
Blind Estimation of a Doubly Selective OFDM Channel: A Deep Learning Algorithm and Theory T. Getu N. Golmie D. Griffith 172 2 0 30 May 2022
Precise Learning Curves and Higher-Order Scaling Limits for Dot Product Kernel RegressionJournal of Statistical Mechanics: Theory and Experiment (JSTAT), 2022 Lechao Xiao Hong Hu Theodor Misiakiewicz Yue M. Lu Jeffrey Pennington 276 21 0 30 May 2022
Robust Weight Perturbation for Adversarial TrainingInternational Joint Conference on Artificial Intelligence (IJCAI), 2022 Chaojian Yu Bo Han Biwei Huang Li Shen Shiming Ge Bo Du Tongliang Liu AAML 152 42 0 30 May 2022
A Blessing of Dimensionality in Membership Inference through RegularizationInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 Jasper Tan Daniel LeJeune Blake Mason Hamid Javadi Richard G. Baraniuk 159 21 0 27 May 2022
Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive PowerNeural Information Processing Systems (NeurIPS), 2022 Binghui Li Jikai Jin Han Zhong John E. Hopcroft Liwei Wang OOD 261 31 0 27 May 2022
On the Inconsistency of Kernel Ridgeless Regression in Fixed DimensionsSIAM Journal on Mathematics of Data Science (SIMODS), 2022 Daniel Beaglehole M. Belkin Parthe Pandit 189 11 0 26 May 2022
A Framework for Overparameterized Learning Dávid Terjék Diego González-Sánchez MLT 170 2 0 26 May 2022
Mirror Descent Maximizes Generalized Margin and Can Be Implemented EfficientlyNeural Information Processing Systems (NeurIPS), 2022 Haoyuan Sun Kwangjun Ahn Christos Thrampoulidis Navid Azizan OOD 176 25 0 25 May 2022
Surprises in adversarially-trained linear regression Antônio H. Ribeiro Dave Zachariah Thomas B. Schon AAML 387 3 0 25 May 2022
Informed Pre-Training on Prior Knowledge Laura von Rueden Sebastian Houben K. Cvejoski Christian Bauckhage Nico Piatkowski 167 7 0 23 May 2022
Stability of the scattering transform for deformations with minimal regularity F. Nicola S. I. Trapasso 182 7 0 23 May 2022
Symmetry Teleportation for Accelerated OptimizationNeural Information Processing Systems (NeurIPS), 2022 B. Zhao Nima Dehmamy Robin Walters Rose Yu ODL 385 28 0 21 May 2022
Consistent Interpolating Ensembles via the Manifold-Hilbert KernelNeural Information Processing Systems (NeurIPS), 2022 Yutong Wang Clayton D. Scott 120 3 0 19 May 2022
Large Neural Networks Learning from Scratch with Very Few Data and without Explicit RegularizationInternational Conference on Machine Learning and Computing (ICMLC), 2022 C. Linse T. Martinetz SSL VLM 110 4 0 18 May 2022
Deep learning of quantum entanglement from incomplete measurementsScience Advances (Sci Adv), 2022 Dominik Koutný L. Ginés M. Moczała-Dusanowska Sven Höfling Christian Schneider Ana Predojevic M. Ježek 442 40 0 03 May 2022
High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the RepresentationNeural Information Processing Systems (NeurIPS), 2022 Jimmy Ba Murat A. Erdogdu Taiji Suzuki Zhichao Wang Denny Wu Greg Yang MLT 236 114 0 03 May 2022
A Falsificationist Account of Artificial Neural NetworksBritish Journal for the Philosophy of Science (BJPS), 2022 O. Buchholz Eric Raidl AI4CE 112 7 0 03 May 2022
Bias-Variance Decompositions for Margin LossesInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 Danny Wood Tingting Mu Gavin Brown UQCV 132 7 0 26 Apr 2022