2011 Poster Sessions : A Hybrid Method for Distance Metric Learning

Student Name : Edward Yihao Kao
Advisor : Benjamin Van Roy
Research Areas: Information Systems
We consider the problem of learning a measure of distance among vectors in a feature space and propose a hybrid method that simultaneously learns from similarity ratings assigned to pairs of vectors and class labels assigned to individual vectors. Our method is based on a generative model in which class labels can provide information that is not encoded in feature vectors but yet relates to perceived similarity between objects. Experiments with synthetic data as well as a real medical image retrieval problem demonstrate that leveraging class labels through use of our method improves retrieval performance significantly.

Yi-hao Kao is a PhD candidate advised by Professor Benjamin Van Roy in the Electrical Engineering Department, Stanford University. His research interests include machine learning, optimization, and, in particular, statistical methods that enhance decision quality. He received his B.S. in Electrical Engineering from National Taiwan University in 2006, and has worked as an intern in Google, Yahoo, and Goldman Sachs.