Skip to content. | Skip to navigation

Personal tools

Sections

UMR 5672

logo de l'ENS de Lyon
logo du CNRS
You are here: Home / Seminars / Machine Learning and Signal Processing / Spectral norm estimation in deep learning

Spectral norm estimation in deep learning

Blaise Delattre (PHD Student - FOXSTREAM - Université Paris Dauphine - PSL)
When Jun 06, 2024
from 01:00 to 02:00
Attendees Blaise Delattre
Add event to calendar vCal
iCal

 

Blaise Delattre

Title: Spectral norm estimation in deep learning

Abstract: This work leverages the use of Gram iteration, an efficient, deterministic, and differentiable method for computing spectral norm with an upper bound guarantee. Designed for dense matrix and circular convolutional layers, we generalize the use of the Gram iteration to zero padding convolutional layers and prove its quadratic convergence. We also provide theorems for bridging the gap between circular and zero padding convolution's spectral norm. We design a spectral rescaling that can be used as a competitive -Lipschitz layer that enhances network robustness. Demonstrated through experiments, our method outperforms state-of-the-art techniques in precision, computational cost, and scalability.

Website: https://scholar.google.com/citations?hl=fr&user=0SNA45sAAAAJ&view_op=list_works&sortby=pubdate

In Room M7.101 of Monod campus, ENSL.