Author

Itay Safran

View on Semantic Scholar

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 Aug 2026

Every Layer Counts: An Exponential $L_2$ Depth Hierarchy for ReLU Networks

A depth hierarchy for ReLU neural networks in which every additional ReLU layer can save exponentially many neurons is proved, and the first exponential separation for ReLU networks between two fixed depths whose shallower network has depth at least $3 is proved.

Itay Safran · 0 citations