Linear inference problems with deterministic constraints

Abstract

Methods are described for the solution of linear inference problems subject to deterministic constraints. The approach builds on work by Backus (1970a,b,c) and Parker (1977), but a range useful advances are suggested to address both conceptual and practical issues. The theory is motivated by, and illustrated with, the estimation of a finite number of a function's spherical harmonic coefficients from a finite set of its point values. Numerical examples are included to demonstrate that the methods can be efficiently applied to realistic problems.