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. 1806.03665
76
3

Identifiability in Gaussian Graphical Models

10 June 2018
D. Soh
S. Tatikonda
ArXiv (abs)PDFHTML
Abstract

In high-dimensional graph learning problems, some topological properties of the graph, such as bounded node degree or tree structure, are typically assumed to hold so that the sample complexity of recovering the graph structure can be reduced. With bounded degree or separability assumptions, quantified by a measure kkk, a ppp-dimensional Gaussian graphical model (GGM) can be learnt with sample complexity Ω(k log p)\Omega (k \: \text{log} \: p)Ω(klogp). Our work in this paper aims to do away with these assumptions by introducing an algorithm that can identify whether a GGM indeed has these topological properties without any initial topological assumptions. We show that we can check whether a GGM has node degree bounded by kkk with sample complexity Ω(k log p)\Omega (k \: \text{log} \: p)Ω(klogp). More generally, we introduce the notion of a strongly K-separable GGM, and show that our algorithm can decide whether a GGM is strongly kkk-separable or not, with sample complexity Ω(k log p)\Omega (k \: \text{log} \: p)Ω(klogp). We introduce the notion of a generalized feedback vertex set (FVS), an extension of the typical FVS, and show that we can use this identification technique to learn GGMs with generalized FVSs.

View on arXiv
Comments on this paper