Papers citing 'Representing smooth functions as compositions of near-identity functions with implications for deep network optimization'

Title
Smooth Model Compression without Fine-Tuning Christina Runkel Natacha Kuete Meli Jovita Lukasik A. Biguri Carola-Bibiane Schönlieb Michael Moeller 197 0 0 30 May 2025
Multi-Label Out-of-Distribution Detection with Spectral Normalized Joint Energy Yihan Mei Xinyu Wang De-Fu Zhang Xiaoling Wang OODD 256 5 0 08 May 2024
An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models Yufeng Zhang Boyi Liu Qi Cai Lingxiao Wang Zhaoran Wang 281 14 0 30 Dec 2022
An Entropy-Based Model for Hierarchical LearningJournal of machine learning research (JMLR), 2022 Amir-Reza Asadi 157 2 0 30 Dec 2022
A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-AwarenessJournal of machine learning research (JMLR), 2022 J. Liu Shreyas Padhy Jie Jessie Ren Zi Lin Yeming Wen Ghassen Jerfel Zachary Nado Jasper Snoek Dustin Tran Balaji Lakshminarayanan UQCV BDL 452 62 0 01 May 2022
Convergence and Implicit Regularization Properties of Gradient Descent for Deep Residual NetworksSocial Science Research Network (SSRN), 2022 R. Cont Alain Rossier Renyuan Xu MLT 301 6 0 14 Apr 2022
Out of Distribution Data Detection Using Dropout Bayesian Neural NetworksAAAI Conference on Artificial Intelligence (AAAI), 2022 A. Nguyen Fred Lu Gary Lopez Munoz Edward Raff Charles K. Nicholas James Holt UQCV 172 28 0 18 Feb 2022
On Measuring Excess Capacity in Neural NetworksNeural Information Processing Systems (NeurIPS), 2022 Florian Graf Sebastian Zeng Bastian Rieck Marc Niethammer Roland Kwitt 289 11 0 16 Feb 2022
Architecture Matters in Continual Learning Seyed Iman Mirzadeh Arslan Chaudhry Dong Yin Timothy Nguyen Razvan Pascanu Dilan Görür Mehrdad Farajtabar OOD KELM 353 63 0 01 Feb 2022
DeDUCE: Generating Counterfactual Explanations Efficiently Benedikt Höltgen Lisa Schut J. Brauner Y. Gal CML 141 6 0 29 Nov 2021
Error Bounds for a Matrix-Vector Product Approximation with Deep ReLU Neural Networks T. Getu 186 2 0 25 Nov 2021
Overparameterization of deep ResNet: zero loss and mean-field analysisJournal of machine learning research (JMLR), 2021 Zhiyan Ding Shi Chen Qin Li S. Wright ODL 188 28 0 30 May 2021
A case for new neural network smoothness constraints Mihaela Rosca T. Weber Arthur Gretton S. Mohamed AAML 299 59 0 14 Dec 2020
Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness Jeremiah Zhe Liu Zi Lin Shreyas Padhy Dustin Tran Tania Bedrax-Weiss Balaji Lakshminarayanan UQCV BDL 747 514 0 17 Jun 2020
A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From DepthInternational Conference on Machine Learning (ICML), 2020 Yiping Lu Chao Ma Yulong Lu Jianfeng Lu Lexing Ying MLT 257 83 0 11 Mar 2020
Machine Learning from a Continuous ViewpointScience China Mathematics (Sci. China Math.), 2019 E. Weinan Chao Ma Lei Wu 254 110 0 30 Dec 2019
GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation Jiawei Zhang Lin Meng 210 55 0 12 Sep 2019
Towards Understanding the Importance of Shortcut Connections in Residual NetworksNeural Information Processing Systems (NeurIPS), 2019 Tianyi Liu Minshuo Chen Mo Zhou S. Du Enlu Zhou T. Zhao 171 48 0 10 Sep 2019
Are deep ResNets provably better than linear predictors?Neural Information Processing Systems (NeurIPS), 2019 Chulhee Yun S. Sra Ali Jadbabaie 259 13 0 09 Jul 2019
Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Nets Amir-Reza Asadi Emmanuel Abbe BDL AI4CE 152 13 0 26 Jun 2019
Data Driven Governing Equations Approximation Using Deep Neural Networks Tong Qin Kailiang Wu D. Xiu PINN 187 289 0 13 Nov 2018
Interpreting Deep Learning: The Machine Learning Rorschach Test? Adam S. Charles AAML HAI AI4CE 190 9 0 01 Jun 2018
Norm-Preservation: Why Residual Networks Can Become Extremely Deep? Alireza Zaeemzadeh Nazanin Rahnavard M. Shah 139 73 0 18 May 2018
Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks Peter L. Bartlett D. Helmbold Philip M. Long 294 121 0 16 Feb 2018