English

Conditional mean embeddings and optimal feature selection via positive definite kernels

Machine Learning 2023-05-16 v1 Functional Analysis

Abstract

Motivated by applications, we consider here new operator theoretic approaches to Conditional mean embeddings (CME). Our present results combine a spectral analysis-based optimization scheme with the use of kernels, stochastic processes, and constructive learning algorithms. For initially given non-linear data, we consider optimization-based feature selections. This entails the use of convex sets of positive definite (p.d.) kernels in a construction of optimal feature selection via regression algorithms from learning models. Thus, with initial inputs of training data (for a suitable learning algorithm,) each choice of p.d. kernel KK in turn yields a variety of Hilbert spaces and realizations of features. A novel idea here is that we shall allow an optimization over selected sets of kernels KK from a convex set CC of positive definite kernels KK. Hence our \textquotedblleft optimal\textquotedblright{} choices of feature representations will depend on a secondary optimization over p.d. kernels KK within a specified convex set CC.

Keywords

Cite

@article{arxiv.2305.08100,
  title  = {Conditional mean embeddings and optimal feature selection via positive definite kernels},
  author = {Palle E. T. Jorgensen and Myung-Sin Song and James Tian},
  journal= {arXiv preprint arXiv:2305.08100},
  year   = {2023}
}

Comments

19 pages, 2 figures

R2 v1 2026-06-28T10:33:56.663Z