AI RESEARCH
Towards The Implicit Bias on Multiclass Separable Data Under Norm Constraints
arXiv CS.LG
•
ArXi:2603.22824v1 Announce Type: new Implicit bias induced by gradient-based algorithms is essential to the generalization of overparameterized models, yet its mechanisms can be subtle. This work leverages the Normalized Steepest Descent} (NSD) framework to investigate how optimization geometry shapes solutions on multiclass separable data. We