Meta learning of bounds on the Bayes classifier error
This work provides incremental improvements in estimating Bayes error bounds for tasks like classifier selection and feature selection in machine learning.
The paper tackled the problem of estimating bounds on the Bayes classifier error by applying meta learning to improve slow plug-in estimators, achieving parametric convergence rates, and empirically compared these bounds on simulated data and image features from sunspot analysis.
Meta learning uses information from base learners (e.g. classifiers or estimators) as well as information about the learning problem to improve upon the performance of a single base learner. For example, the Bayes error rate of a given feature space, if known, can be used to aid in choosing a classifier, as well as in feature selection and model selection for the base classifiers and the meta classifier. Recent work in the field of f-divergence functional estimation has led to the development of simple and rapidly converging estimators that can be used to estimate various bounds on the Bayes error. We estimate multiple bounds on the Bayes error using an estimator that applies meta learning to slowly converging plug-in estimators to obtain the parametric convergence rate. We compare the estimated bounds empirically on simulated data and then estimate the tighter bounds on features extracted from an image patch analysis of sunspot continuum and magnetogram images.