Query by Committee, Linear Separation and Random Walks

Abstract. Recent works have shown the advantage of using Active Learning methods, such as the Query by Committee (QBC) algorithm, to various learning problems. This class of Algorithms requires an oracle with the ability to randomly select a consistent hypothesis according to some prede ned distribution. When trying to implement such an oracle, for the linear separators family of hypotheses, various problems should be solved. The major problem is time-complexity, where the straight-forward Monte Carlo method takes exponential time. In this paper we address some of those problems and show how to convert them to the problems of sampling from convex bodies or approximating the volume of such bodies. We show that recent algorithms for approximating the volume of convex bodies and approximately uniformly sampling from convex bodies using random walks, can be used to solve this problem, and yield an e cient implementation for the QBC algorithm. This solution suggests a connection between ran...

• Type: Conference
• Year: 1999
• Where: EUROCOLT
• Authors: Ran Bachrach, Shai Fine, Eli Shamir
• Keywords: Convex Bodies, EUROCOLT 1999, Machine Learning, Random Walks, Various Learning Problems