Part of Advances in Neural Information Processing Systems 21 (NIPS 2008)
J. Bagnell, David Bradley
Prior work has shown that features which appear to be biologically plausible as well as empirically useful can be found by sparse coding with a prior such as a laplacian (L1) that promotes sparsity. We show how smoother priors can pre- serve the benefits of these sparse priors while adding stability to the Maximum A-Posteriori (MAP) estimate that makes it more useful for prediction problems. Additionally, we show how to calculate the derivative of the MAP estimate effi- ciently with implicit differentiation. One prior that can be differentiated this way is KL-regularization. We demonstrate its effectiveness on a wide variety of appli- cations, and find that online optimization of the parameters of the KL-regularized model can significantly improve prediction performance.