Recovery Conditions and Sampling Strategies for Network Lasso

TL;DR

This paper introduces the network compatibility condition, a new criterion linking network topology and sampling strategies to ensure accurate recovery of clustered signals using network Lasso, enhancing understanding of data sampling in network-structured learning.

Contribution

It generalizes the compatibility condition for Lasso to network Lasso, providing a theoretical basis for optimal sampling strategies based on network topology.

Findings

Derived the network compatibility condition for network Lasso

Linked sampling node placement to network clustering structure

Provided guidelines for selecting informative data points

Abstract

The network Lasso is a recently proposed convex optimization method for machine learning from massive network structured datasets, i.e., big data over networks. It is a variant of the well-known least absolute shrinkage and selection operator (Lasso), which is underlying many methods in learning and signal processing involving sparse models. Highly scalable implementations of the network Lasso can be obtained by state-of-the art proximal methods, e.g., the alternating direction method of multipliers (ADMM). By generalizing the concept of the compatibility condition put forward by van de Geer and Buehlmann as a powerful tool for the analysis of plain Lasso, we derive a sufficient condition, i.e., the network compatibility condition, on the underlying network topology such that network Lasso accurately learns a clustered underlying graph signal. This network compatibility condition relates the location of the sampled nodes with the clustering structure of the network. In particular, the NCC informs the choice of which nodes to sample, or in machine learning terms, which data points provide most information if labeled.