Kernel Mean Embeddings of Von Neumann-Algebra-Valued Measures
arXiv:2007.14698
Abstract
Kernel mean embedding (KME) is a powerful tool to analyze probability measures for data, where the measures are conventionally embedded into a reproducing kernel Hilbert space (RKHS). In this paper, we generalize KME to that of von Neumann-algebra-valued measures into reproducing kernel Hilbert modules (RKHMs), which provides an inner product and distance between von Neumann-algebra-valued measures. Von Neumann-algebra-valued measures can, for example, encode relations between arbitrary pairs of variables in a multivariate distribution or positive operator-valued measures for quantum mechanics. Thus, this allows us to perform probabilistic analyses explicitly reflected with higher-order interactions among variables, and provides a way of applying machine learning frameworks to problems in quantum mechanics. We also show that the injectivity of the existing KME and the universality of RKHS are generalized to RKHM, which confirms many useful features of the existing KME remain in our generalized KME. And, we investigate the empirical performance of our methods using synthetic and real-world data.
References in corpus (7)
- Quantum Information and Relativity Theory
- Quantum machine learning for quantum anomaly detection
- Eigendecompositions of Transfer Operators in Reproducing Kernel Hilbert Spaces
- Inferring the quantum density matrix with machine learning
- Geometry of quantum state space and quantum correlations
- Krylov Subspace Method for Nonlinear Dynamical Systems with Random Noise
- Analysis via Orthonormal Systems in Reproducing Kernel Hilbert -Modules and Applications