Skip to content
conftrace_
2020 AAAI AAAI 2020

A Bias Trick for Centered Robust Principal Component Analysis (Student Abstract)

Abstract

Abstract Outlier based Robust Principal Component Analysis (RPCA) requires centering of the non-outliers. We show a “bias trick” that automatically centers these non-outliers. Using this bias trick we obtain the first RPCA algorithm that is optimal with respect to centering.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization

Authors

Baokun He, Guihong Wan, Haim Schweitzer

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Optimization & Theory > Optimization Mathematics & Optimization > Mathematics > Linear Algebra Machine Learning > Core Methods > Dimensionality Reduction Machine Learning > Core Methods > Matrix Factorization Machine Learning > Core Methods > Anomaly Detection

Keywords

matrix decomposition dimensionality reduction outlier detection matrix completion robust principal component analysis
Download PDF

More from AAAI 2020

All AAAI 2020 papers →
Hypergraph Convolutional Network for Multi-Hop Knowledge Base Question Answering (Student Abstract)
Trimodal Attention Module for Multimodal Sentiment Analysis (Student Abstract)
Action Graphs for Goal Recognition Problems with Inaccurate Initial States (Student Abstract)
Inception LSTM for Next-frame Video Prediction (Student Abstract)
Multi-View Deep Attention Network for Reinforcement Learning (Student Abstract)
Streaming Batch Gradient Tracking for Neural Network Training (Student Abstract)