v1v2v3v4v5v6 (latest)

On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length

13 July 2018

Stanislaw Jastrzebski

Amos Storkey

Papers citing "On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length"

45 / 45 papers shown

Title
Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More Geonhui Yoo Minhak Song Chulhee Yun FAtt 22 0 0 07 Jun 2025
SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation Dahun Shin Dongyeop Lee Jinseok Chung Namhoon Lee ODL AAML 510 0 0 25 Feb 2025
Does SGD really happen in tiny subspaces? Minhak Song Kwangjun Ahn Chulhee Yun 118 7 1 25 May 2024
Visualizing, Rethinking, and Mining the Loss Landscape of Deep Neural Networks Yichu Xu Xin-Chun Li Lan Li De-Chuan Zhan 87 2 0 21 May 2024
Training-time Neuron Alignment through Permutation Subspace for Improving Linear Mode Connectivity and Model Fusion Zexi Li Zhiqi Li Jie Lin Tao Shen Tao Lin Chao Wu 126 5 0 02 Feb 2024
Stochastic Modified Equations and Dynamics of Dropout Algorithm Zhongwang Zhang Yuqing Li Yaoyu Zhang Z. Xu 45 9 0 25 May 2023
Evolutionary Algorithms in the Light of SGD: Limit Equivalence, Minima Flatness, and Transfer Learning Andrei Kucharavy R. Guerraoui Ljiljana Dolamic 104 1 0 20 May 2023
Revisiting Weighted Aggregation in Federated Learning with Neural Networks Zexi Li Tao R. Lin Xinyi Shang Chao-Xiang Wu FedML 102 65 0 14 Feb 2023
Communication-Efficient Federated Learning for Heterogeneous Edge Devices Based on Adaptive Gradient Quantization Heting Liu Fang He Guohong Cao FedML MQ 82 27 0 16 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
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability Alexandru Damian Eshaan Nichani Jason D. Lee 107 88 0 30 Sep 2022
Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes M. Kodryan E. Lobacheva M. Nakhodnov Dmitry Vetrov 105 17 0 08 Sep 2022
Adaptive Gradient Methods at the Edge of Stability Jeremy M. Cohen Behrooz Ghorbani Shankar Krishnan Naman Agarwal Sourabh Medapati ... Daniel Suo David E. Cardoze Zachary Nado George E. Dahl Justin Gilmer ODL 103 54 0 29 Jul 2022
Dataset Condensation via Efficient Synthetic-Data Parameterization Jang-Hyun Kim Jinuk Kim Seong Joon Oh Sangdoo Yun Hwanjun Song Joonhyun Jeong Jung-Woo Ha Hyun Oh Song DD 518 168 0 30 May 2022
Understanding the unstable convergence of gradient descent Kwangjun Ahn J.N. Zhang S. Sra 88 63 0 03 Apr 2022
It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher Kanghyun Choi Hye Yoon Lee Deokki Hong Joonsang Yu Noseong Park Youngsok Kim Jinho Lee MQ 101 33 0 31 Mar 2022
Complexity from Adaptive-Symmetries Breaking: Global Minima in the Statistical Mechanics of Deep Neural Networks Shaun Li AI4CE 71 0 0 03 Jan 2022
An Empirical Investigation of the Role of Pre-training in Lifelong Learning Sanket Vaibhav Mehta Darshan Patil Sarath Chandar Emma Strubell CLL 148 145 0 16 Dec 2021
Critical Learning Periods in Federated Learning Gang Yan Hao Wang Jian Li FedML 82 8 0 12 Sep 2021
The Limiting Dynamics of SGD: Modified Loss, Phase Space Oscillations, and Anomalous Diffusion D. Kunin Javier Sagastuy-Breña Lauren Gillespie Eshed Margalit Hidenori Tanaka Surya Ganguli Daniel L. K. Yamins 93 20 0 19 Jul 2021
Regularization in ResNet with Stochastic Depth Soufiane Hayou Fadhel Ayed 57 10 0 06 Jun 2021
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Xiangning Chen Cho-Jui Hsieh Boqing Gong ViT 108 330 0 03 Jun 2021
Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability Jeremy M. Cohen Simran Kaur Yuanzhi Li J. Zico Kolter Ameet Talwalkar ODL 131 279 0 26 Feb 2021
Consensus Control for Decentralized Deep Learning Lingjing Kong Tao R. Lin Anastasia Koloskova Martin Jaggi Sebastian U. Stich 53 79 0 09 Feb 2021
Combating Mode Collapse in GAN training: An Empirical Analysis using Hessian Eigenvalues Ricard Durall Avraam Chatzimichailidis P. Labus J. Keuper GAN 77 62 0 17 Dec 2020
Geometry Perspective Of Estimating Learning Capability Of Neural Networks Ankan Dutta Arnab Rakshit 36 1 0 03 Nov 2020
Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification Saurabh Agarwal Hongyi Wang Kangwook Lee Shivaram Venkataraman Dimitris Papailiopoulos 85 25 0 29 Oct 2020
Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks Yikai Wu Xingyu Zhu Chenwei Wu Annie Wang Rong Ge 114 45 0 08 Oct 2020
Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra Vardan Papyan 64 80 0 27 Aug 2020
Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training Diego Granziol S. Zohren Stephen J. Roberts ODL 148 50 0 16 Jun 2020
Understanding the Role of Training Regimes in Continual Learning Seyed Iman Mirzadeh Mehrdad Farajtabar Razvan Pascanu H. Ghasemzadeh CLL 81 228 0 12 Jun 2020
Learning Rate Annealing Can Provably Help Generalization, Even for Convex Problems Preetum Nakkiran MLT 64 21 0 15 May 2020
Analyzing the discrepancy principle for kernelized spectral filter learning algorithms Alain Celisse Martin Wahl 65 18 0 17 Apr 2020
On Learning Rates and Schrödinger Operators Bin Shi Weijie J. Su Michael I. Jordan 90 61 0 15 Apr 2020
Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule Nikhil Iyer V. Thejas Nipun Kwatra Ramachandran Ramjee Muthian Sivathanu 75 29 0 09 Mar 2020
The Implicit and Explicit Regularization Effects of Dropout Colin Wei Sham Kakade Tengyu Ma 116 118 0 28 Feb 2020
The Break-Even Point on Optimization Trajectories of Deep Neural Networks Stanislaw Jastrzebski Maciej Szymczak Stanislav Fort Devansh Arpit Jacek Tabor Kyunghyun Cho Krzysztof J. Geras 88 164 0 21 Feb 2020
Emergent properties of the local geometry of neural loss landscapes Stanislav Fort Surya Ganguli 120 51 0 14 Oct 2019
Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin Colin Wei Tengyu Ma AAML OOD 72 85 0 09 Oct 2019
GradVis: Visualization and Second Order Analysis of Optimization Surfaces during the Training of Deep Neural Networks Avraam Chatzimichailidis Franz-Josef Pfreundt N. Gauger J. Keuper 52 10 0 26 Sep 2019
Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization Xinyan Li Qilong Gu Yingxue Zhou Tiancong Chen A. Banerjee ODL 88 52 0 24 Jul 2019
Large Scale Structure of Neural Network Loss Landscapes Stanislav Fort Stanislaw Jastrzebski 74 84 0 11 Jun 2019
Stiffness: A New Perspective on Generalization in Neural Networks Stanislav Fort Pawel Krzysztof Nowak Stanislaw Jastrzebski S. Narayanan 133 94 0 28 Jan 2019
Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians Vardan Papyan 82 88 0 24 Jan 2019
Laplacian Smoothing Gradient Descent Stanley Osher Bao Wang Penghang Yin Xiyang Luo Farzin Barekat Minh Pham A. Lin ODL 113 43 0 17 Jun 2018