On monotone `metrics' of the classical channel space:non-asymptotic theory
Keiji Matsumoto

TL;DR
This paper characterizes monotone metrics in the space of classical channels without relying on the inner-product assumption, revealing that such metrics cannot be true metrics and establishing bounds for specific examples.
Contribution
It introduces a new axiomatic framework for monotone metrics on channels that does not assume inner products, and identifies bounds and limitations of these metrics.
Findings
Largest and smallest 'metrics' are not induced from inner products.
Any 'metric' satisfying the axioms cannot be a true metric.
Provides bounds for specific channel examples.
Abstract
The aim of the manuscript is to characterize monotone `metric' in the space of Markov map. Here, `metric' means the square of the norm defined on the tangent space, and not necessarily induced from an inner product (this property hereafter will be called inner-product-assumption), different from usual metric used in differential geometry. As for metrics in So far, there have been plenty of literatures on the metric in the space of probability distributions and quantum states. Among them, Cencov proved the monotone metric in probability distribution space is unique up to constant multiple, and identical to Fisher information metric. Petz characterized all the monotone metrics in the quantum state space using operator mean. As for channels, however, only a little had been known. In this paper, we impose monotonicity by concatenation of channels before and after the given channel families,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMathematical functions and polynomials · Mathematical Inequalities and Applications · Functional Equations Stability Results
