Minimum Relative Entropy Inference for Normal and Monte Carlo Distributions

24 Pages Posted: 17 Nov 2019 Last revised: 28 Dec 2019

See all articles by Marcello Colasante

Marcello Colasante

ARPM - Advanced Risk and Portfolio Management

Attilio Meucci

ARPM - Advanced Risk and Portfolio Management

Date Written: December 27, 2019

Abstract

We represent affine sub-manifolds of exponential family distributions as minimum relative entropy sub-manifolds. With such representation we derive analytical formulas for the inference from partial information on expectations and covariances of multivariate normal distributions; and we improve the numerical implementation via Monte Carlo simulations for the inference from partial information of generalized expectation type.

Keywords: Minimum Relative Entropy, Kullback-Leibler, Hamiltonian Monte Carlo, Flexible Probabilities, Exponential-Family Distributions

JEL Classification: C1, G11

Suggested Citation

Colasante, Marcello and Meucci, Attilio, Minimum Relative Entropy Inference for Normal and Monte Carlo Distributions (December 27, 2019). Available at SSRN: https://ssrn.com/abstract=3479693 or http://dx.doi.org/10.2139/ssrn.3479693

Marcello Colasante (Contact Author)

ARPM - Advanced Risk and Portfolio Management ( email )

New York, NY
United States

HOME PAGE: http://www.arpm.co

Attilio Meucci

ARPM - Advanced Risk and Portfolio Management ( email )

HOME PAGE: http://www.arpm.co/

Register to save articles to
your library

Register

Paper statistics

Downloads
22
Abstract Views
143
PlumX Metrics