NEURAL COLLAPSE IN DEEP HOMOGENEOUS CLASSIFIERS AND THE ROLE OF WEIGHT DECAY

Akshay Rangamani, Andrzej Banburski-Fahey

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Scopus citations

Abstract

Neural Collapse is a phenomenon recently discovered in deep classifiers where the last layer activations collapse onto their class means, while the means and last layer weights take on the structure of dual equiangular tight frames. In this paper we present results showing the role of weight decay in the emergence of Neural Collapse in deep homogeneous networks. We show that certain near-interpolating minima of deep networks satisfy the Neural Collapse condition, and this can be derived from the gradient flow on the regularized square loss. We also show that weight decay is necessary for neural collapse to occur. We support our theoretical analysis with experiments that confirm our results.

Original languageEnglish (US)
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4243-4247
Number of pages5
ISBN (Electronic)9781665405409
DOIs
StatePublished - 2022
Externally publishedYes
Event47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, Singapore
Duration: May 23 2022May 27 2022

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Country/TerritorySingapore
CityVirtual, Online
Period5/23/225/27/22

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Keywords

  • Classification
  • Deep Learning
  • Inductive Bias
  • Neural Collapse
  • Weight Decay

Fingerprint

Dive into the research topics of 'NEURAL COLLAPSE IN DEEP HOMOGENEOUS CLASSIFIERS AND THE ROLE OF WEIGHT DECAY'. Together they form a unique fingerprint.

Cite this