We propose a method for feature selection that employs kernel-based measures of independence to find a subset of covariates that is maximally predictive of the response. Building on past work in kernel dimension reduction, we show how to perform feature selection via a constrained optimization problem involving the trace of the conditional covariance operator. We prove various consistency results for this procedure, and also demonstrate that our method compares favorably with other state-of-the-art algorithms on a variety of synthetic and real data sets.

We develop a class of algorithms, as variants of the stochastically controlled stochastic gradient (SCSG) methods [21], for the smooth non-convex finitesum optimization problem.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/