Matrix Completion under Interval Uncertainty

Abstract

Matrix completion under interval uncertainty can be cast as matrix completion with element-wise box constraints. We present an efficient alternating-direction parallel coordinate-descent method for the problem. We show that the method outperforms any other known method on a benchmark in image in-painting in terms of signal-to-noise ratio, and that it provides high-quality solutions for an instance of collaborative filtering with 100,198,805 recommendations within 5 minutes.

References in corpus (7)

• Proceedings of the 29th International Conference on Machine Learning (ICML-12)
• HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
• On the Complexity of Best Arm Identification in Multi-Armed Bandit Models
• Distributed Coordinate Descent Method for Learning with Big Data
• Large-Scale Convex Minimization with a Low-Rank Constraint
• Distributed Block Coordinate Descent for Minimizing Partially Separable Functions
• Spectral Compressed Sensing via Structured Matrix Completion

Cited by in corpus (3)

• Best Pair Formulation & Accelerated Scheme for Non-convex Principal Component Pursuit
• Low-Rank Methods in Event Detection and Subsampled Point-to-Subspace Proximity Tests
• Clipped Matrix Completion: A Remedy for Ceiling Effects