Matrix Completion Under Monotonic Single Index Models

TL;DR

This paper introduces a matrix completion method that effectively handles nonlinear distortions by alternating between low-rank estimation and monotonic function estimation, with theoretical error bounds and empirical validation.

Contribution

It proposes a novel approach for matrix completion under unknown monotonic nonlinear transformations, extending traditional low-rank assumptions.

Findings

Method achieves competitive accuracy on synthetic datasets.

Theoretical bounds relate estimation error to matrix size and rank.

Empirical results validate effectiveness on real-world data.

Abstract

Most recent results in matrix completion assume that the matrix under consideration is low-rank or that the columns are in a union of low-rank subspaces. In real-world settings, however, the linear structure underlying these models is distorted by a (typically unknown) nonlinear transformation. This paper addresses the challenge of matrix completion in the face of such nonlinearities. Given a few observations of a matrix that are obtained by applying a Lipschitz, monotonic function to a low rank matrix, our task is to estimate the remaining unobserved entries. We propose a novel matrix completion method that alternates between low-rank matrix estimation and monotonic function estimation to estimate the missing matrix elements. Mean squared error bounds provide insight into how well the matrix can be estimated based on the size, rank of the matrix and properties of the nonlinear transformation. Empirical results on synthetic and real-world datasets demonstrate the competitiveness of the proposed approach.