Low bias bagged support vector machines

Theoretical and experimental analyses of bagging indicate that it is primarily a variance reduction technique. This suggests that bagging should be applied to learning algorithms tuned to minimize bias, even at the cost of some increase in variance. We test this idea with Support Vector Machines (SVMs) by employing out-of-bag estimates of bias and variance to tune the SVMs. Experiments indicate that bagging of low-bias SVMs (the “lobag” algorithm) never hurts generalization performance and often improves it compared with well-tuned single SVMs and to bags of individually well-tuned SVMs.