Exact spectral norm regularization for neural networks
Preprint, 2022

We pursue a line of research that seeks to regularize the spectral norm of the Jacobian of the input-output mapping for deep neural networks. While previous work rely on upper bounding techniques, we provide a scheme that targets the exact
spectral norm. We showcase that our algorithm achieves an improved generalization performance compared to previous spectral regularization techniques while simultaneously maintaining a strong safeguard against natural and adversarial
noise. Moreover, we further explore some previous reasoning concerning the strong adversarial protection that Jacobian regularization provides and show that it can be misleading.

Författare

Anton Johansson

Chalmers, Matematiska vetenskaper, Tillämpad matematik och statistik

Niklas Engsner

Chalmers, Data- och informationsteknik, Data Science

Claes Strannegård

Chalmers, Data- och informationsteknik, Data Science och AI

Petter Mostad

Chalmers, Matematiska vetenskaper, Tillämpad matematik och statistik

Ämneskategorier

Annan matematik

Mer information

Senast uppdaterat

2023-10-27