ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2410.20646
26
0

Injectivity capacity of ReLU gates

28 October 2024
Mihailo Stojnic
ArXivPDFHTML
Abstract

We consider the injectivity property of the ReLU networks layers. Determining the ReLU injectivity capacity (ratio of the number of layer's inputs and outputs) is established as isomorphic to determining the capacity of the so-called ℓ0\ell_0ℓ0​ spherical perceptron. Employing \emph{fully lifted random duality theory} (fl RDT) a powerful program is developed and utilized to handle the ℓ0\ell_0ℓ0​ spherical perceptron and implicitly the ReLU layers injectivity. To put the entire fl RDT machinery in practical use, a sizeable set of numerical evaluations is conducted as well. The lifting mechanism is observed to converge remarkably fast with relative corrections in the estimated quantities not exceeding ∼0.1%\sim 0.1\%∼0.1% already on the third level of lifting. Closed form explicit analytical relations among key lifting parameters are uncovered as well. In addition to being of incredible importance in handling all the required numerical work, these relations also shed a new light on beautiful parametric interconnections within the lifting structure. Finally, the obtained results are also shown to fairly closely match the replica predictions from [40].

View on arXiv
Comments on this paper