EcoSta 2018: Registration
View Submission - EcoSta2018
Title: Online learning for supervised dimension reduction Authors:  Qiang Wu - Middle Tennessee State University (United States) [presenting]
Ning Zhang - Middle Tennessee State University (United States)
Abstract: Supervised dimension reduction is an effective tool for high dimension data analysis. It enables easy visualization of the data and improves predictive power of subsequent analyses by other statistical machine learning algorithms. As high dimensional and big data become ubiquitous in modern sciences, it is necessary to develop fast and dynamic supervised dimension reduction methods. We will present two new methods that implement dimension reduction in an online learning manner. These methods are much faster than batch learning methods while achieve comparable performance.