A Compositional Kernel Model for Feature Learning

The paper introduces a compositional variant of kernel ridge regression where the predictor reweights input coordinates, framing the approach as a variational problem to study feature learning in compositional architectures. It demonstrates that both global minimizers and stationary points can discard Gaussian noise variables while retaining relevant ones, and shows that α1-type kernels (e.g., Laplace) recover features contributing to nonlinear effects at stationary points, whereas Gaussian kernels recover only linear ones.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.