A convex formulation for learning scale-free networks via submodular relaxation

Date

2012

Authors

Defazio, Aaron
Caetano, Tiberio

Journal Title

Journal ISSN

Volume Title

Publisher

Neural Information Processing Systems Foundation

Abstract

A key problem in statistics and machine learning is the determination of network structure from data. We consider the case where the structure of the graph to be reconstructed is known to be scale-free. We show that in such cases it is natural to formulat

Description

Keywords

Keywords: Convex optimization problems; Convex relaxation; Gaussian graphical models; Network structures; Scale free networks; Structured sparsities; Submodular functions; Tractable class; Convex optimization; Relaxation processes

Citation

Source

NEURAL INFORMATION PROCESSING SYSTEMS. Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012

Type

Conference paper

Book Title

Entity type

Access Statement

Open Access

License Rights

DOI

Restricted until