SRN

2000년 도입 · 논문 17편에서 사용

Stable Rank Normalization (SRN) is a weight-normalization scheme which minimizes the stable rank of a linear operator. It simultaneously controls the Lipschitz constant and the stable rank of a linear operator. Stable rank is a softer version of the rank operator and is defined as the squared ratio of the Frobenius norm to the spectral norm.

출처: Stable Rank Normalization for Improved Generalization in Neural Networks and GANs

소개 논문: Stable Rank Normalization for Improved Generalization in Neural Networks and GANs