Self-Paced Probabilistic Principal Component Analysis for Data with Outliers
arXiv:1904.06546
Abstract
Principal Component Analysis (PCA) is a popular tool for dimensionality reduction and feature extraction in data analysis. There is a probabilistic version of PCA, known as Probabilistic PCA (PPCA). However, standard PCA and PPCA are not robust, as they are sensitive to outliers. To alleviate this problem, this paper introduces the Self-Paced Learning mechanism into PPCA, and proposes a novel method called Self-Paced Probabilistic Principal Component Analysis (SP-PPCA). Furthermore, we design the corresponding optimization algorithm based on the alternative search strategy and the expectation-maximization algorithm. SP-PPCA looks for optimal projection vectors and filters out outliers iteratively. Experiments on both synthetic problems and real-world datasets clearly demonstrate that SP-PPCA is able to reduce or eliminate the impact of outliers.
References in corpus (7)
- Scikit-learn: Machine Learning in Python
- Efficient L1-Norm Principal-Component Analysis via Bit Flipping
- Self Paced Deep Learning for Weakly Supervised Object Detection
- A Novel M-Estimator for Robust PCA
- Bridging Saliency Detection to Weakly Supervised Object Detection Based on Self-paced Curriculum Learning
- What Objective Does Self-paced Learning Indeed Optimize?
- Online Robust Principal Component Analysis with Change Point Detection