Joint estimation of smooth graph signals from partial linear measurements

TL;DR

This paper develops a method for jointly estimating smooth graph signals from limited linear measurements, providing theoretical guarantees for recovery even with sparse and partial data, applicable to ranking problems.

Contribution

It introduces non-asymptotic bounds for smooth graph signal recovery from partial measurements, extending to multi-layer ranking with sparse measurement graphs.

Findings

Estimator is weakly consistent as the number of vertices grows.

Effective even with very sparse and disconnected measurement graphs.

Provides non-asymptotic mean squared error bounds.

Abstract

Given an undirected and connected graph $G$ on $T$ vertices, suppose each vertex $t$ has a latent signal $x_t \in \mathbb{R}^n$ associated to it. Given partial linear measurements of the signals, for a potentially small subset of the vertices, our goal is to estimate $x_t$'s. Assuming that the signals are smooth w.r.t $G$, in the sense that the quadratic variation of the signals over the graph is small, we obtain non-asymptotic bounds on the mean squared error for jointly recovering $x_t$'s, for the smoothness penalized least squares estimator. In particular, this implies for certain choices of $G$ that this estimator is weakly consistent (as $T \rightarrow \infty$) under potentially very stringent sampling, where only one coordinate is measured per vertex for a vanishingly small fraction of the vertices. The results are extended to a ``multi-layer'' ranking problem where $x_t$ corresponds to the latent strengths of a collection of $n$ items, and noisy pairwise difference measurements are obtained at each ``layer'' $t$ via a measurement graph $G_t$. Weak consistency is established for certain choices of $G$ even when the individual $G_t$'s are very sparse and disconnected.