The Positive-Definite Completion Problem
Kartik G. Waghmare, Victor M. Panaretos

TL;DR
This paper investigates the positive-definite completion problem for kernels, establishing existence, uniqueness, and characterizations of solutions, including a canonical completion analogous to determinant-maximizing matrix completions.
Contribution
It introduces the concept of a canonical completion for kernels, providing algebraic and variational characterizations and proving its existence and uniqueness under specific domain conditions.
Findings
Existence of canonical completion for domains containing the diagonal band
Uniqueness of the canonical completion under certain conditions
Characterizations of solutions via algebraic and variational methods
Abstract
We study the positive-definite completion problem for kernels on a variety of domains and prove results concerning the existence, uniqueness, and characterization of solutions. In particular, we study a special solution called the canonical completion which is the reproducing kernel analogue of the determinant-maximizing completion known to exist for matrices. We establish several results concerning its existence and uniqueness, which include algebraic and variational characterizations. Notably, we prove the existence of a canonical completion for domains which are equivalent to the band containing the diagonal. This corresponds to the existence of a canonical extension in the context of the classical extension problem of positive-definite functions, which can be understood as the solution to an abstract Cauchy problem in a certain reproducing kernel Hilbert space.
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
TopicsContact Mechanics and Variational Inequalities · Numerical methods in inverse problems · Optimization and Variational Analysis
