Assessing Generalization of SGD via Disagreement

Assessing Generalization of SGD via Disagreement

25 June 2021

Vaishnavh Nagarajan

J. Zico Kolter

Papers citing "Assessing Generalization of SGD via Disagreement"

17 / 17 papers shown

Title
Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention Alexander Koebler Thomas Decker Ingo Thon Volker Tresp Florian Buettner 29 0 0 11 May 2025
Performance Estimation in Binary Classification Using Calibrated Confidence Juhani Kivimäki Jakub Białek W. Kuberski J. Nurminen 48 0 0 08 May 2025
Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors Shuangpeng Han Mengmi Zhang 116 0 0 03 Oct 2024
Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift Renchunzi Xie Ambroise Odonnat Vasilii Feofanov I. Redko Jianfeng Zhang Bo An UQCV 72 1 0 17 Jan 2024
On the Variance of Neural Network Training with respect to Test Sets and Distributions Keller Jordan OOD 18 10 0 04 Apr 2023
Demystifying Disagreement-on-the-Line in High Dimensions Dong-Hwan Lee Behrad Moniri Xinmeng Huang Edgar Dobriban Hamed Hassani 21 8 0 31 Jan 2023
Task Discovery: Finding the Tasks that Neural Networks Generalize on Andrei Atanov Andrei Filatov Teresa Yeo Ajay Sohmshetty Amir Zamir OOD 40 10 0 01 Dec 2022
ModelDiff: A Framework for Comparing Learning Algorithms Harshay Shah Sung Min Park Andrew Ilyas A. Madry SyDa 51 26 0 22 Nov 2022
Variation-based Cause Effect Identification Mohamed Amine ben Salem Karim Barsim Bin Yang CML 24 0 0 22 Nov 2022
Git Re-Basin: Merging Models modulo Permutation Symmetries Samuel K. Ainsworth J. Hayase S. Srinivasa MoMe 252 313 0 11 Sep 2022
On the Strong Correlation Between Model Invariance and Generalization Weijian Deng Stephen Gould Liang Zheng OOD 32 16 0 14 Jul 2022
Detecting Label Errors by using Pre-Trained Language Models Derek Chong Jenny Hong Christopher D. Manning NoLa 38 21 0 25 May 2022
A Note on "Assessing Generalization of SGD via Disagreement" Andreas Kirsch Y. Gal FedML UQCV 21 15 0 03 Feb 2022
Datamodels: Predicting Predictions from Training Data Andrew Ilyas Sung Min Park Logan Engstrom Guillaume Leclerc A. Madry TDI 38 130 0 01 Feb 2022
A Framework for Cluster and Classifier Evaluation in the Absence of Reference Labels R. Joyce Edward Raff Charles K. Nicholas 41 16 0 23 Sep 2021
Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles Jiefeng Chen Frederick Liu Besim Avci Xi Wu Yingyu Liang S. Jha 24 61 0 29 Jun 2021
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles Balaji Lakshminarayanan Alexander Pritzel Charles Blundell UQCV BDL 276 5,660 0 05 Dec 2016