Purushottam Kar
Date: Friday, October 28th, 2011
Time: 5:15 PM
Venue: CS101.
We consider the problem of classification using similarity/distance functions over data. Specifically, we propose a framework for defining the goodness of a (dis)similarity function with respect to a given learning task and propose algorithms that have guaranteed generalization properties when working with such good functions. Our framework unifies and generalizes the frameworks proposed by (Balcan-Blum ICML 2006) and (Wang et al ICML 2007). An attractive feature of our framework is its adaptability to data.
We show, by giving theoretical guarantees, that the goodness criterion best suited to a problem can itself be learned which makes our approach applicable to a variety of domains and problems. We demonstrate the effectiveness of our goodness criteria learning method on a variety of similarity-based learning datasets and benchmark UCI datasets on which our method consistently outperforms existing approaches by a significant margin.
This is joint work with Prateek Jain, Microsoft Research Labs India.