Bad Global Minima Exist and SGD Can Reach Them

6 June 2019

Papers citing "Bad Global Minima Exist and SGD Can Reach Them"

22 / 22 papers shown

Title
Position: A taxonomy for reporting and describing AI security incidents L. Bieringer Kevin Paeth Andreas Wespi Kathrin Grosse Alexandre Alahi Kathrin Grosse 88 0 0 19 Dec 2024
Spectral regularization for adversarially-robust representation learning Sheng Yang Jacob A. Zavatone-Veth Cengiz Pehlevan AAML OOD 54 0 0 27 May 2024
Medical Image Classification Using Transfer Learning and Chaos Game Optimization on the Internet of Medical Things Alhassan Mabrouk Abdelghani Dahou M. A. Abd Elaziz R. D. Díaz Redondo Mohammed Kayed 21 20 0 12 Dec 2023
Maintaining Plasticity in Continual Learning via Regenerative Regularization Saurabh Kumar Henrik Marklund Benjamin Van Roy CLL KELM 39 18 0 23 Aug 2023
Sharpness-Aware Graph Collaborative Filtering Huiyuan Chen Chin-Chia Michael Yeh Yujie Fan Yan Zheng Junpeng Wang Vivian Lai Mahashweta Das Hao Yang 36 5 0 18 Jul 2023
Layer-wise Linear Mode Connectivity Linara Adilova Maksym Andriushchenko Michael Kamp Asja Fischer Martin Jaggi FedML FAtt MoMe 43 15 0 13 Jul 2023
How to escape sharp minima with random perturbations Kwangjun Ahn Ali Jadbabaie S. Sra ODL 34 6 0 25 May 2023
Abrupt and spontaneous strategy switches emerge in simple regularised neural networks Anika T. Lowe Léo Touzo Paul S. Muhle-Karbe Andrew M. Saxe Christopher Summerfield Nicolas W. Schuck 13 5 0 22 Feb 2023
mSAM: Micro-Batch-Averaged Sharpness-Aware Minimization Kayhan Behdin Qingquan Song Aman Gupta S. Keerthi Ayan Acharya Borja Ocejo Gregory Dexter Rajiv Khanna D. Durfee Rahul Mazumder AAML 23 7 0 19 Feb 2023
Label driven Knowledge Distillation for Federated Learning with non-IID Data Minh-Duong Nguyen Viet Quoc Pham D. Hoang Long Tran-Thanh Diep N. Nguyen W. Hwang 28 2 0 29 Sep 2022
Stabilizing Off-Policy Deep Reinforcement Learning from Pixels Edoardo Cetin Philip J. Ball Steve Roberts Oya Celiktutan 38 36 0 03 Jul 2022
Neural Networks can Learn Representations with Gradient Descent Alexandru Damian Jason D. Lee Mahdi Soltanolkotabi SSL MLT 25 114 0 30 Jun 2022
Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction Kaifeng Lyu Zhiyuan Li Sanjeev Arora FAtt 52 71 0 14 Jun 2022
Towards Understanding Sharpness-Aware Minimization Maksym Andriushchenko Nicolas Flammarion AAML 35 134 0 13 Jun 2022
Learning through atypical "phase transitions" in overparameterized neural networks Carlo Baldassi Clarissa Lauditi Enrico M. Malatesta R. Pacelli Gabriele Perugini R. Zecchina 36 26 0 01 Oct 2021
What can linear interpolation of neural network loss landscapes tell us? Tiffany J. Vlaar Jonathan Frankle MoMe 30 27 0 30 Jun 2021
Revisiting Model Stitching to Compare Neural Representations Yamini Bansal Preetum Nakkiran Boaz Barak FedML 49 107 0 14 Jun 2021
Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification Francesca Mignacco Florent Krzakala Pierfrancesco Urbani Lenka Zdeborová MLT 17 66 0 10 Jun 2020
Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization S. Chatterjee ODL OOD 11 51 0 25 Feb 2020
Consensus-Based Optimization on Hypersurfaces: Well-Posedness and Mean-Field Limit M. Fornasier Hui-Lin Huang L. Pareschi Philippe Sünnen 13 54 0 31 Jan 2020
Consensus-Based Optimization on the Sphere: Convergence to Global Minimizers and Machine Learning M. Fornasier Hui Huang L. Pareschi Philippe Sünnen 29 68 0 31 Jan 2020
SGD on Neural Networks Learns Functions of Increasing Complexity Preetum Nakkiran Gal Kaplun Dimitris Kalimeris Tristan Yang Benjamin L. Edelman Fred Zhang Boaz Barak MLT 28 236 0 28 May 2019