Low rank estimation of smooth kernels on graphs

The Annals of Statistics · 2013 · Volume 41 · Issue 2

Abstract

Let $(V,A)$ be a weighted graph with a finite vertex set $V$, with a symmetric matrix of nonnegative weights $A$ and with Laplacian $\Delta$. Let $S_{\ast}: V\times V\mapsto{\mathbb{R}}$ be a symmetric kernel defined on the vertex set $V$. Consider $n$ i.i.d. observations $(X_{j},X_{j}',Y_{j})$, $j=1,\ldots,n$, where $X_{j}$, $X_{j}'$ are independent random vertices sampled from the uniform distribution in $V$ and $Y_{j}\in{\mathbb{R}}$ is a real valued response variable such that ${\mathbb{E}}(Y_{j}|X_{j},X_{j}')=S_{\ast}(X_{j},X_{j}')$, $j=1,\ldots,n$. The goal is to estimate the kernel $S_{\ast}$ based on the data $(X_{1},X_{1}',Y_{1}),\ldots,(X_{n},X_{n}',Y_{n})$ and under the assumption that $S_{\ast}$ is low rank and, at the same time, smooth on the graph (the smoothness being characterized by discrete Sobolev norms defined in terms of the graph Laplacian). We obtain several results for such problems including minimax lower bounds on the $L_{2}$-error and upper bounds for penalized least squares estimators both with nonconvex and with convex penalties.

Keywords

60B20, 60G15, 62H12, 62J99, discrete Sobolev norm, graph Laplacian, low-rank matrix estimation, Matrix completion, matrix Lasso, minimax error bound, nuclear norm, optimal error rate

Enable JavaScript for citation tools and additional paper interactions.