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. 2306.13520
65
3

On the Convergence Rate of Gaussianization with Random Rotations

23 June 2023
Felix Dräxler
Lars Kühmichel
Armand Rousselot
Jens Müller
Christoph Schnörr
Ullrich Kothe
ArXiv (abs)PDFHTML
Abstract

Gaussianization is a simple generative model that can be trained without backpropagation. It has shown compelling performance on low dimensional data. As the dimension increases, however, it has been observed that the convergence speed slows down. We show analytically that the number of required layers scales linearly with the dimension for Gaussian input. We argue that this is because the model is unable to capture dependencies between dimensions. Empirically, we find the same linear increase in cost for arbitrary input p(x)p(x)p(x), but observe favorable scaling for some distributions. We explore potential speed-ups and formulate challenges for further research.

View on arXiv
Comments on this paper