点击次数：

论文类型：期刊论文

发表时间：2019-08-01

发表刊物：NEURAL NETWORKS

收录刊物：SCIE、PubMed、EI

卷号：116

页面范围：246-256

ISSN号：0893-6080

关键字：Bayesian model; Generalized double Pareto; LRR; Low-rank; RPCA

摘要：Rank minimization is a key component of many computer vision and machine learning methods, including robust principal component analysis (RPCA) and low-rank representations (LRR). However, usual methods rely on optimization to produce a point estimate without characterizing uncertainty in this estimate, and also face difficulties in tuning parameter choice. Both of these limitations are potentially overcome with Bayesian methods, but there is currently a lack of general purpose Bayesian approaches for rank penalization. We address this gap using a positive generalized double Pareto prior, illustrating the approach in RPCA and LRR. Posterior computation relies on hybrid Gibbs sampling and geodesic Monte Carlo algorithms. We assess performance in simulation examples, and benchmark data sets. (C) 2019 Elsevier Ltd. All rights reserved.