Towards moderate overparameterization: global convergence guarantees for training shallow neural networks

12 February 2019

Papers citing "Towards moderate overparameterization: global convergence guarantees for training shallow neural networks"

50 / 132 papers shown

Title
Implicit Regularization of the Deep Inverse Prior Trained with Inertia Nathan Buskulic Jalal Fadil Yvain Quéau 38 1 0 03 Jun 2025
Curse of Dimensionality in Neural Network Optimization Sanghoon Na Haizhao Yang 84 0 0 07 Feb 2025
The Persistence of Neural Collapse Despite Low-Rank Bias: An Analytic Perspective Through Unconstrained Features Connall Garrod Jonathan P. Keating 65 4 0 30 Oct 2024
Reparameterization invariance in approximate Bayesian inference Hrittik Roy M. Miani Carl Henrik Ek Philipp Hennig Marvin Pfortner Lukas Tatzel Søren Hauberg BDL 119 9 0 05 Jun 2024
Clinical Domain Knowledge-Derived Template Improves Post Hoc AI Explanations in Pneumothorax Classification Han Yuan Chuan Hong Pengtao Jiang Gangming Zhao Nguyen Tuan Anh Tran Xinxing Xu Yet Yen Yan Nan Liu 62 11 0 26 Mar 2024
Understanding the Double Descent Phenomenon in Deep Learning Marc Lafon Alexandre Thomas 94 2 0 15 Mar 2024
Capacity of the treelike sign perceptrons neural networks with one hidden layer -- RDT based upper bounds M. Stojnic 51 4 0 13 Dec 2023
Fundamental Limits of Deep Learning-Based Binary Classifiers Trained with Hinge Loss T. Getu Georges Kaddoum M. Bennis 89 1 0 13 Sep 2023
Random feature approximation for general spectral methods Mike Nguyen Nicole Mücke 48 1 0 29 Aug 2023
Six Lectures on Linearized Neural Networks Theodor Misiakiewicz Andrea Montanari 134 13 0 25 Aug 2023
Convergence of Two-Layer Regression with Nonlinear Units Yichuan Deng Zhao Song Shenghao Xie 80 7 0 16 Aug 2023
Memory capacity of two layer neural networks with smooth activations Liam Madden Christos Thrampoulidis MLT 47 5 0 03 Aug 2023
Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer Yuandong Tian Yiping Wang Beidi Chen S. Du MLT 107 79 0 25 May 2023
Fast Convergence in Learning Two-Layer Neural Networks with Separable Data Hossein Taheri Christos Thrampoulidis MLT 49 3 0 22 May 2023
Convergence Guarantees of Overparametrized Wide Deep Inverse Prior Nathan Buskulic Yvain Quéau M. Fadili BDL 68 2 0 20 Mar 2023
Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron Weihang Xu S. Du 102 16 0 20 Feb 2023
Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks Shuai Zhang Ming Wang Pin-Yu Chen Sijia Liu Songtao Lu Miaoyuan Liu MLT 105 17 0 06 Feb 2023
Over-parameterised Shallow Neural Networks with Asymmetrical Node Scaling: Global Convergence Guarantees and Feature Learning François Caron Fadhel Ayed Paul Jung Hoileong Lee Juho Lee Hongseok Yang 121 2 0 02 Feb 2023
Learning Lipschitz Functions by GD-trained Shallow Overparameterized ReLU Neural Networks Ilja Kuzborskij Csaba Szepesvári 73 4 0 28 Dec 2022
Learning threshold neurons via the "edge of stability" Kwangjun Ahn Sébastien Bubeck Sinho Chewi Y. Lee Felipe Suarez Yi Zhang MLT 103 41 0 14 Dec 2022
Matching DNN Compression and Cooperative Training with Resources and Data Availability F. Malandrino G. Giacomo Armin Karamzade Marco Levorato C. Chiasserini 106 9 0 02 Dec 2022
Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing Josh Alman Jiehao Liang Zhao Song Ruizhe Zhang Danyang Zhuo 136 31 0 25 Nov 2022
Spectral Evolution and Invariance in Linear-width Neural Networks Zhichao Wang A. Engel Anand D. Sarwate Ioana Dumitriu Tony Chiang 114 18 0 11 Nov 2022
Cold Start Streaming Learning for Deep Networks Cameron R. Wolfe Anastasios Kyrillidis CLL 55 2 0 09 Nov 2022
Finite Sample Identification of Wide Shallow Neural Networks with Biases M. Fornasier T. Klock Marco Mondelli Michael Rauchensteiner 47 6 0 08 Nov 2022
A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks Zhengdao Chen Eric Vanden-Eijnden Joan Bruna MLT 75 5 0 28 Oct 2022
When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work Jiawei Zhang Yushun Zhang Mingyi Hong Ruoyu Sun Zhi-Quan Luo 122 10 0 21 Oct 2022
On skip connections and normalisation layers in deep optimisation L. MacDonald Jack Valmadre Hemanth Saratchandran Simon Lucey ODL 74 2 0 10 Oct 2022
Restricted Strong Convexity of Deep Learning Models with Smooth Activations A. Banerjee Pedro Cisneros-Velarde Libin Zhu M. Belkin 73 8 0 29 Sep 2022
Approximation results for Gradient Descent trained Shallow Neural Networks in $1d$ R. Gentile G. Welper ODL 100 7 0 17 Sep 2022
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) Zhenyu Zhu Fanghui Liu Grigorios G. Chrysos Volkan Cevher 104 21 0 15 Sep 2022
Generalization Properties of NAS under Activation and Skip Connection Search Zhenyu Zhu Fanghui Liu Grigorios G. Chrysos Volkan Cevher AI4CE 90 17 0 15 Sep 2022
A Sublinear Adversarial Training Algorithm Yeqi Gao Lianke Qin Zhao Song Yitan Wang GAN 77 25 0 10 Aug 2022
Training Overparametrized Neural Networks in Sublinear Time Yichuan Deng Han Hu Zhao Song Omri Weinstein Danyang Zhuo BDL 90 28 0 09 Aug 2022
Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity Jianyi Yang Shaolei Ren 73 3 0 02 Jul 2022
Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis Alexander Munteanu Simon Omlor Zhao Song David P. Woodruff 97 15 0 26 Jun 2022
Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime Benjamin Bowman Guido Montúfar 82 15 0 06 Jun 2022
Blind Estimation of a Doubly Selective OFDM Channel: A Deep Learning Algorithm and Theory T. Getu N. Golmie D. Griffith 52 2 0 30 May 2022
Randomly Initialized One-Layer Neural Networks Make Data Linearly Separable Promit Ghosal Srinath Mahankali Yihang Sun MLT 60 5 0 24 May 2022
On Feature Learning in Neural Networks with Global Convergence Guarantees Zhengdao Chen Eric Vanden-Eijnden Joan Bruna MLT 84 13 0 22 Apr 2022
Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models Chaoyue Liu Libin Zhu M. Belkin 53 4 0 10 Mar 2022
S-Rocket: Selective Random Convolution Kernels for Time Series Classification Hojjat Salehinejad Yang Wang Yuanhao Yu Jingshan Tang S. Valaee AI4TS 56 15 0 07 Mar 2022
On the Omnipresence of Spurious Local Minima in Certain Neural Network Training Problems C. Christof Julia Kowalczyk 77 8 0 23 Feb 2022
Improved Overparametrization Bounds for Global Convergence of Stochastic Gradient Descent for Shallow Neural Networks Bartlomiej Polaczyk J. Cyranka ODL 54 3 0 28 Jan 2022
Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks Benjamin Bowman Guido Montúfar 106 11 0 12 Jan 2022
AutoBalance: Optimized Loss Functions for Imbalanced Data Mingchen Li Xuechen Zhang Christos Thrampoulidis Jiasi Chen Samet Oymak 66 68 0 04 Jan 2022
Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time Zhao Song Licheng Zhang Ruizhe Zhang 112 66 0 14 Dec 2021
On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons Fangshuo Liao Anastasios Kyrillidis 118 16 0 05 Dec 2021
Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models Tri Dao Beidi Chen Kaizhao Liang Jiaming Yang Zhao Song Atri Rudra Christopher Ré 130 79 0 30 Nov 2021
SGD Through the Lens of Kolmogorov Complexity Gregory Schwartzman 75 1 0 10 Nov 2021