Signal recovery from pooling representations

Joan Bruna, Arthur Szlam, Yann Lecun

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

Abstract

In this work we compute lower Lipschitz bounds of lp pooling operators for p = 1,2, ∞ as well as lp pooling operators preceded by half- rectification layers. These give sufficient conditions for the design of invertible neural network layers. Numerical experiments on MNIST and image patches confirm that pooling layers can be inverted with phase recovery algorithms. Moreover, the regularity of the inverse pooling, controlled by the lower Lipschitz constant, is empirically verified with a nearest neighbor regression.

Original languageEnglish (US)
Title of host publication31st International Conference on Machine Learning, ICML 2014
PublisherInternational Machine Learning Society (IMLS)
Pages1585-1598
Number of pages14
ISBN (Electronic)9781634393973
StatePublished - 2014
Event31st International Conference on Machine Learning, ICML 2014 - Beijing, China
Duration: Jun 21 2014Jun 26 2014

Publication series

Name31st International Conference on Machine Learning, ICML 2014
Volume2

Other

Other31st International Conference on Machine Learning, ICML 2014
CountryChina
CityBeijing
Period6/21/146/26/14

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Software

Fingerprint Dive into the research topics of 'Signal recovery from pooling representations'. Together they form a unique fingerprint.

  • Cite this

    Bruna, J., Szlam, A., & Lecun, Y. (2014). Signal recovery from pooling representations. In 31st International Conference on Machine Learning, ICML 2014 (pp. 1585-1598). (31st International Conference on Machine Learning, ICML 2014; Vol. 2). International Machine Learning Society (IMLS).