Evidence integrals are a key ingredient of quantified maximum entropy (QME). They allow the evaluation of hyper-parameters which in turn determine the amount of regularization, the noise level, confidence intervals, etc. Consequently, the exact evaluation of those multidimensional integrals is of central importance to the theory. Since the conventional steepest descent (SD) approximation fails frequently a more refined approach is needed. Using diagrammatic techniques we derive a correction factor to the SD result which is readily incorporated in existing QME codes and which provides significantly improved results.
Bibliographic Reference: Article: Maximum Entropy and Bayesian Methods (1996) pp. 443-448
Record Number: 199710066 / Last updated on: 1997-02-26
Original language: en
Available languages: en