Events

Maximal Width Learning of Binary Functions

00:00 06-12-2006

The maximal-margin approach of machine learning is the basis of several successful algorithms such as Support Vector Machines which have recently been very popular due to their good generalization ability. In this talk I will describe how this approach may be used for learning directly binary functions from a finite labeled sample $zeta$ of cardinality $m$. I will introduce a new concept of sample {em width} which is similar to the notion of margin for real-valued functions. Our result shows that learning binary functions by maximizing the width yields improved upper bound on the generalization error. Compared to existing bounds on maximal-margin learners (for instance, via thresholding of real-valued functions) our bound is significantly better and excludes the usual $O(ln(m))$ factor. This is joint work with Prof. Martin Anthony from the department of Mathematics, London School of Economics.

Add to calendar

Outlook

Google

Back to Home

Events

Maximal Width Learning of Binary Functions

About HIT

Faculties & Departments

Undergraduate Programs

Graduate Programs

Quick links