Online Choice of Active Learning Algorithms
Yoram Baram, Ran El Yaniv, Kobi Luz; 5(Mar):255--291, 2004.
Abstract
This work is concerned with the question of how to combine online
an ensemble of active learners so as to expedite the learning
progress in pool-based active learning. We develop an
active-learning master algorithm, based on a known competitive algorithm
for the multi-armed bandit problem. A major challenge in
successfully choosing top performing active learners online is to
reliably estimate their progress during the learning session. To this
end we propose a simple maximum entropy criterion that provides
effective estimates in realistic settings. We study the
performance of the proposed master algorithm using an ensemble
containing two of the best known active-learning algorithms as
well as a new algorithm. The resulting active-learning master
algorithm is empirically shown to consistently perform almost as
well as and sometimes outperform the best algorithm in the
ensemble on a range of classification problems.
[abs][pdf][ps.gz][ps]