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. 1801.02901
32
0
v1v2 (latest)

Convexification of Neural Graph

9 January 2018
Han Xiao
    GNN
ArXiv (abs)PDFHTML
Abstract

Traditionally, most complex intelligence architectures are extremely non-convex, which could not be well performed by convex optimization. However, this paper decomposes complex structures into three types of nodes: operators, algorithms and functions. Further, iteratively propagating from node to node along edge, we prove that "regarding the neural graph without triangles, it is nearly convex in each variable, when the other variables are fixed." In fact, the non-convex properties stem from triangles and functions, which could be transformed to be convex with our proposed \textit{\textbf{convexification inequality}}. In conclusion, we generally depict the landscape for the objective of neural graph and propose the methodology to convexify neural graph.

View on arXiv
Comments on this paper