Networks Aren't Scale-Invariant, So Why Do Scale-Inspired Methods Work?

Jianlin Chen noted neural networks aren't scale-invariant since L(w)=L(cw) doesn't hold, prompting discussion on why scale-invariance-inspired methods still prove so effective.

2026-11-10 ~ 2026-11-10 · 2 related posts

• Networks aren't scale invariant — so why has scale invariance motivated so many useful methods? — jasondeanlee · 2026-11-10
• Networks Aren't Scale Invariant, Yet Countless Methods Assume It — Why? — Jianlin_S · 2026-11-10