A Theoretical Analysis of the Learning Dynamics under Class Imbalance

v1v2v3v4 (latest)

A Theoretical Analysis of the Learning Dynamics under Class Imbalance

International Conference on Machine Learning (ICML), 2022

1 July 2022

Emanuele Francazi

Aurelien Lucchi

ArXiv (abs)PDF HTML

Papers citing "A Theoretical Analysis of the Learning Dynamics under Class Imbalance"

13 / 13 papers shown

Title
GRASP: Guided Residual Adapters with Sample-wise Partitioning Felix Nützel Mischa Dombrowski Bernhard Kainz MedIm 92 0 0 01 Dec 2025
Imbalanced Classification through the Lens of Spurious Correlations Jakob Hackstein Sidney Bender 96 0 0 31 Oct 2025
When majority rules, minority loses: bias amplification of gradient descent François Bachoc Jérôme Bolte Ryan Boustany Jean-Michel Loubes FaML 369 1 0 19 May 2025
Class Imbalance in Anomaly Detection: Learning from an Exactly Solvable ModelInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2025 F.S. Pezzicoli V. Ros F.P. Landes M. Baity-Jesi 311 2 0 20 Jan 2025
When resampling/reweighting improves feature learning in imbalanced classification?: A toy-model study Tomoyuki Obuchi Toshiyuki Tanaka 289 2 0 09 Sep 2024
Early learning of the optimal constant solution in neural networks and humans Jirko Rubruck Jan P. Bauer Andrew M. Saxe Christopher Summerfield 330 4 0 25 Jun 2024
Minimizing Energy Costs in Deep Learning Model Training: The Gaussian Sampling Approach Challapalli Phanindra Revanth Sumohana S. Channappayya C Krishna Mohan 172 23 0 11 Jun 2024
Restoring balance: principled under/oversampling of data for optimal classificationInternational Conference on Machine Learning (ICML), 2024 Emanuele Loffredo Mauro Pastore Simona Cocco R. Monasson 252 13 0 15 May 2024
Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models Frederik Kunstner Robin Yadav Alan Milligan Mark Schmidt Alberto Bietti 315 60 0 29 Feb 2024
Gradient Reweighting: Towards Imbalanced Class-Incremental Learning Jiangpeng He Fengqing Zhu CLL 336 35 0 28 Feb 2024
Understanding the Role of Layer Normalization in Label-Skewed Federated Learning Guojun Zhang Mahdi Beitollahi Alex Bie Xi Chen FedML MLT AI4CE 149 4 0 18 Aug 2023
Can Continual Learning Improve Long-Tailed Recognition? Toward a Unified Framework Mahdiyar Molahasani Michael A. Greenspan Ali Etemad 121 2 0 23 Jun 2023
Initial Guessing Bias: How Untrained Networks Favor Some ClassesInternational Conference on Machine Learning (ICML), 2023 Emanuele Francazi Aurelien Lucchi Carlo Albert AI4CE 251 8 0 01 Jun 2023