Kernel Trace Distance: Quantum Statistical Metric between Measures through RKHS Density Operators

This seminar presents Mr. Arturo Castellanos Salinas' research on "Kernel Trace Distance: Quantum Statistical Metric between Measures through RKHS Density Operators." Explore how quantum statistical metrics can be applied to measure distances between probability distributions using Reproducing Kernel Hilbert Space (RKHS) density operators. The 43-minute talk, part of the "Representing, calibrating & leveraging prediction uncertainty from statistics to machine learning" event series at the Isaac Newton Institute, delves into advanced mathematical concepts that bridge quantum statistics and machine learning. Scheduled for May 28th, 2025, from 17:00 to 18:30, this presentation offers valuable insights for researchers and practitioners working at the intersection of quantum information theory, statistical learning, and uncertainty quantification.