English

Infinite-dimensional Log-Determinant divergences II: Alpha-Beta divergences

Functional Analysis 2017-01-17 v2 Artificial Intelligence Information Theory math.IT Machine Learning

Abstract

This work presents a parametrized family of divergences, namely Alpha-Beta Log- Determinant (Log-Det) divergences, between positive definite unitized trace class operators on a Hilbert space. This is a generalization of the Alpha-Beta Log-Determinant divergences between symmetric, positive definite matrices to the infinite-dimensional setting. The family of Alpha-Beta Log-Det divergences is highly general and contains many divergences as special cases, including the recently formulated infinite dimensional affine-invariant Riemannian distance and the infinite-dimensional Alpha Log-Det divergences between positive definite unitized trace class operators. In particular, it includes a parametrized family of metrics between positive definite trace class operators, with the affine-invariant Riemannian distance and the square root of the symmetric Stein divergence being special cases. For the Alpha-Beta Log-Det divergences between covariance operators on a Reproducing Kernel Hilbert Space (RKHS), we obtain closed form formulas via the corresponding Gram matrices.

Keywords

Cite

@article{arxiv.1610.08087,
  title  = {Infinite-dimensional Log-Determinant divergences II: Alpha-Beta divergences},
  author = {Minh Ha Quang},
  journal= {arXiv preprint arXiv:1610.08087},
  year   = {2017}
}

Comments

71 pages

R2 v1 2026-06-22T16:31:46.746Z