On the Comparison of Optimizers for Imbalanced Learning

stat.ML

Submitted: 2026-10-05

Updated: 2026-10-05

Code: https://github.com/karpathy/nanoGPT

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Decoupling Representation and Classifier for Long-Tailed Recognition
• Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives
• Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness
• Muon in Vision Transformers: Optimizer-Recipe Interactions and Gradient Spectra
• LLaMA: Open and Efficient Foundation Language Models
• How Muon's Spectral Design Benefits Generalization: A Study on Imbalanced Data
• Muon Outperforms Adam in Tail-End Associative Memory Learning
• Lack of differentiability of semigroups associated to delayed abstract thermoelastic systems

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier