Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations

Abstract

Non-negative matrix factorization is a basic tool for decomposing data into the feature and weight matrices under non-negativity constraints, and in practice is often solved in the alternating minimization framework. However, it is unclear whether such algorithms can recover the ground-truth feature matrix when the weights for different features are highly correlated, which is common in applications. This paper proposes a simple and natural alternating gradient descent based algorithm, and shows that with a mild initialization it provably recovers the ground-truth in the presence of strong correlations. In most interesting cases, the correlation can be in the same order as the highest possible. Our analysis also reveals its several favorable features including robustness to noise. We complement our theoretical results with empirical studies on semi-synthetic datasets, demonstrating its advantage over several popular methods in recovering the ground-truth.

arXiv commentAccepted to the International Conference on Machine Learning (ICML), 2017

References in corpus (3)

• Learning Topic Models - Going beyond SVD
• Provable Algorithms for Inference in Topic Models
• Computing a Nonnegative Matrix Factorization -- Provably

Cited by in corpus (6)

• Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
• Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
• What Can ResNet Learn Efficiently, Going Beyond Kernels?
• On the Sublinear Convergence of Randomly Perturbed Alternating Gradient Descent to Second Order Stationary Solutions
• Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions
• Making Method of Moments Great Again? -- How can GANs learn distributions