On a Multiplicative Algorithm for Computing Bayesian D-optimal Designs

We use the minorization-maximization principle (Lange, Hunter and Yang 2000) to establish the monotonicity of a multiplicative algorithm for computing Bayesian D-optimal designs. This proves a conjecture of Dette, Pepelyshev and Zhigljavsky (2008).

💡 Research Summary

The paper addresses the long‑standing open problem of proving monotonicity for a multiplicative algorithm used to compute Bayesian D‑optimal designs. In a Bayesian D‑optimal design one seeks a design measure ξ that maximizes the determinant of the expected information matrix Eπ