A fast, always positive definite and normalizable approximation of non-Gaussian likelihoods

Abstract

In this paper we extent the previously published DALI-approximation for likelihoods to cases in which the parameter dependency is in the covariance matrix. The approximation recovers non-Gaussian likelihoods, and reduces to the Fisher matrix approach in the case of Gaussianity. It works with the minimal assumptions of having Gaussian errors on the data, and a covariance matrix that possesses a converging Taylor approximation. The resulting approximation works in cases of severe parameter degeneracies and in cases where the Fisher matrix is singular. It is at least $1000$ times faster than a typical Monte Carlo Markov Chain run over the same parameter space. Two example applications, to cases of extremely non-Gaussian likelihoods, are presented -- one demonstrates how the method succeeds in reconstructing completely a ring-shaped likelihood. A public code is released here: http://lnasellentin.github.io/DALI/

accepted for publication in MNRAS

References in corpus (4)

• Current status of the Standard Model CKM fit and constraints on $\Delta F=2$ New Physics
• Estimating Cosmological Parameter Covariance
• Estimation of cosmological parameters using adaptive importance sampling
• Breaking the spell of Gaussianity: forecasting with higher order Fisher matrices

Cited by in corpus (21)

• On the insufficiency of arbitrarily precise covariance matrices: non-Gaussian weak lensing likelihoods
• Objective Bayesian analysis of neutrino masses and hierarchy
• Beware of commonly used approximations I: errors in forecasts
• Beware of commonly used approximations II: estimating systematic biases in the best-fit parameters
• Sufficiency of a Gaussian power spectrum likelihood for accurate cosmology from upcoming weak lensing surveys
• Extreme data compression while searching for new physics
• Validating the Fisher approach for stage IV spectroscopic surveys
• A blinding solution for inference from astronomical data
• Extending the Fisher Information Matrix in Gravitational-wave Data Analysis
• Optimizing parameter constraints: a new tool for Fisher matrix forecasts
• Non-Gaussian forecasts of weak lensing with and without priors
• Information geometry in cosmological inference problems
• Generalisations of Fisher Matrices
• Beyond Fisher Forecasting for Cosmology
• Extremely expensive likelihoods: A variational-Bayes solution for precision cosmology
• Partition function approach to non-Gaussian likelihoods: Formalism and expansions for weakly non-Gaussian cosmological inference
• Boosting MonteCarlo sampling with a non-Gaussian fit
• Non-Gaussian statistics in galaxy weak lensing: compressed three-point correlations and cosmological forecasts
• Breaking degeneracies with the Sunyaev-Zeldovich full bispectrum
• MCMC generation of cosmological fields far beyond Gaussianity
• Realistic systematic biases induced by residual intrinsic alignments in cosmic shear surveys