Abstract
Rapid advances in technology have made classification with high dimensional features and ubiquitous problem in modern scientific studies and applications. There are three fundamental goals in the pursuit of a good high-dimensional classifier: accuracy, interpretability, and scalability. In the past 15 years, a host of competitive high-dimensional classifiers have been developed based on sparse regularization techniques. In this article, we give a selective overview of these classification methods. This article is categorized under: Statistical Learning and Exploratory Methods of the Data Sciences > Knowledge Discovery.
Original language | English (US) |
---|---|
Article number | e1453 |
Journal | Wiley Interdisciplinary Reviews: Computational Statistics |
Volume | 11 |
Issue number | 1 |
DOIs | |
State | Published - Jan 1 2019 |
Bibliographical note
Funding Information:This work is supported by NSF grant DMS-1505111. The author thanks three referees for their helpful comments and suggestions.
Publisher Copyright:
© 2018 Wiley Periodicals, Inc.
Keywords
- classification
- feature selection
- penalization
- sparsity