Author

Wei-Kai Chang

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay

Together, these results isolate a single governing quantity for scale-invariant optimization, providing a precise and actionable lens on training dynamics, optimizer behavior, and schedule design in modern deep learning.

H. Amin, Wei-Kai Chang, Rajiv Khanna · 0 citations