Improving Random Projections Using Marginal Information

Abstract. We present an improved version of random projections that takes advantage of marginal norms. Using a maximum likelihood estimator (MLE), marginconstrained random projections can improve estimation accuracy considerably. Theoretical properties of this estimator are analyzed in detail.

• Type: Conference
• Year: 2006
• Where: COLT
• Authors: Ping Li, Trevor Hastie, Kenneth Ward Church
• Keywords: COLT 2006, Machine Learning, Marginal Norms, Maximum Likelihood Estimator, Random Projections