Matrix Completion Under Monotonic Single Index Models

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.

21 pages, 5 figures, 1 table. Accepted for publication at NIPS 2015

References in corpus (2)

• Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
• Least Squares Revisited: Scalable Approaches for Multi-class Prediction

Cited by in corpus (8)

• Fast Algorithms for Demixing Sparse Signals from Nonlinear Observations
• Nonparametric Preference Completion
• Preference Completion from Partial Rankings
• On a low-rank matrix single index model
• On Learning High Dimensional Structured Single Index Models
• Sentiment Analysis by Joint Learning of Word Embeddings and Classifier
• Recommendation via matrix completion using Kolmogorov complexity
• SAR: Semantic Analysis for Recommendation