Viet-Anh on Software Logo

What is: Sparse Switchable Normalization?

SourceSSN: Learning Sparse Switchable Normalization via SparsestMax
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Sparse Switchable Normalization (SSN) is a variant on Switchable Normalization where the importance ratios are constrained to be sparse. Unlike 1\ell_1 and 0\ell_0 constraints that impose difficulties in optimization, the constrained optimization problem is turned into feed-forward computation through SparseMax, which is a sparse version of softmax.