v1v2 (latest)

Understanding Why Neural Networks Generalize Well Through GSNR of Parameters

International Conference on Learning Representations (ICLR), 2020

21 January 2020

Papers citing "Understanding Why Neural Networks Generalize Well Through GSNR of Parameters"

30 / 30 papers shown

GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling

Arash Jamshidi

Lauri Seppäläinen

Katsiaryna Haitsiukevich

221

26 Aug 2025

SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training

290

29 May 2025

DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer

439

21 May 2025

CGLearn: Consistent Gradient-Based Learning for Out-of-Distribution GeneralizationInternational Conference on Pattern Recognition Applications and Methods (ICPRAM), 2024

Jawad Chowdhury

G. Terejanu

AI4CE BDL OOD OODD

429

09 Nov 2024

Adversarial Vulnerability as a Consequence of On-Manifold Inseparibility

265

09 Oct 2024

Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong InformationConference on Empirical Methods in Natural Language Processing (EMNLP), 2024

Yongheng Zhang

Jingxuan Zhou

Libo Qin

398

06 Oct 2024

UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation

Zixuan Li

Jing Xiong

Fanghua Ye

Chuanyang Zheng

Xun Wu

...

Lingpeng Kong

421

03 Oct 2024

Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models

Sha Li

426

10 Jul 2024

Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks

Amit Peleg

Matthias Hein

407

04 Jul 2024

Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability

Rajdeep Haldar

Yue Xing

Qifan Song

368

06 Mar 2024

BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor LearningInternational Journal of Computer Vision (IJCV), 2024

Hongrui Chen

355

26 Jan 2024

Domain Generalization Guided by Gradient Signal to Noise Ratio of ParametersIEEE International Conference on Computer Vision (ICCV), 2023

Mateusz Michalkiewicz

382

11 Oct 2023

Accelerating Large Batch Training via Gradient Signal to Noise Ratio (GSNR)

253

24 Sep 2023

Gradient Mask: Lateral Inhibition Mechanism Improves Performance in Artificial Neural Networks

Lei Jiang

Yongqing Liu

Shihai Xiao

Yansong Chua

223

14 Aug 2022

Deep Learning and Symbolic Regression for Discovering Parametric EquationsIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022

332

01 Jul 2022

BackdoorBench: A Comprehensive Benchmark of Backdoor LearningNeural Information Processing Systems (NeurIPS), 2022

Hongrui Chen

374

213

25 Jun 2022

Exploiting Explainable Metrics for Augmented SGDComputer Vision and Pattern Recognition (CVPR), 2022

Mahdi S. Hosseini

Mathieu Tuli

Konstantinos N. Plataniotis

AAML

318

31 Mar 2022

On the Generalization Mystery in Deep Learning

S. Chatterjee

Piotr Zielinski

OOD

355

18 Mar 2022

Confidence Dimension for Deep Learning based on Hoeffding Inequality and Relative Evaluation

183

17 Mar 2022

Dataset Condensation with Contrastive SignalsInternational Conference on Machine Learning (ICML), 2022

402

137

07 Feb 2022

In Search of Probeable Generalization MeasuresInternational Conference on Machine Learning and Applications (ICMLA), 2021

Jonathan Jaegerman

Khalil Damouni

M. M. Ankaralı

Konstantinos N. Plataniotis

231

23 Oct 2021

Taxonomizing local versus global structure in neural network loss landscapesNeural Information Processing Systems (NeurIPS), 2021

410

23 Jul 2021

Disparity Between Batches as a Signal for Early Stopping

Mahsa Forouzesh

Patrick Thiran

370

14 Jul 2021

Cockpit: A Practical Debugging Tool for the Training of Deep Neural NetworksNeural Information Processing Systems (NeurIPS), 2021

Frank Schneider

Felix Dangel

Philipp Hennig

273

12 Feb 2021

The training accuracy of two-layer neural networks: its estimation and understanding using random datasetsInternational Conference on Artificial Intelligence and Pattern Recognition (AIPR), 2020

Shuyue Guan

Murray H. Loew

166

26 Oct 2020

Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine TranslationConference on Empirical Methods in Natural Language Processing (EMNLP), 2020

Wenxiang Jiao

Xing Wang

Shilin He

Irwin King

Michael R. Lyu

Zhaopeng Tu

222

06 Oct 2020

Analysis of Generalizability of Deep Neural Networks Based on the Complexity of Decision BoundaryInternational Conference on Machine Learning and Applications (ICMLA), 2020

Shuyue Guan

Murray H. Loew

301

16 Sep 2020

A Vision-based Social Distancing and Critical Density Detection System for COVID-19

259

171

07 Jul 2020

Dynamic of Stochastic Gradient Descent with State-Dependent Noise

380

24 Jun 2020

The Break-Even Point on Optimization Trajectories of Deep Neural NetworksInternational Conference on Learning Representations (ICLR), 2020

Stanislaw Jastrzebski

332

195

21 Feb 2020