Inference and Sampling for Archimax Copulas

  title={Inference and Sampling for Archimax Copulas},
  author={Yuting Ng and Ali Hasan and Vahid Tarokh},
Understanding multivariate dependencies in both the bulk and the tails of a distribution is an important problem for many applications, such as ensuring algorithms are robust to observations that are infrequent but have devastating effects. Archimax copulas are a family of distributions endowed with a precise representation that allows simultaneous modeling of the bulk and the tails of a distribution. Rather than separating the two as is typically done in practice, incorporating additional… 



Inference for Archimax copulas

Archimax copula models can account for any type of asymptotic dependence between extremes and at the same time capture joint risks at medium levels. An Archimax copula is characterized by two

Inference-less Density Estimation using Copula Bayesian Networks

This work leverages on the specialized form of the Copula Bayesian Network model to derive a computationally amenable learning objective that is a lower bound on the log-likelihood function, thus facilitating practical learning of highdimensional densities.

Implicit Generative Copulas

This paper proposes a flexible, yet conceptually simple alternative based on implicit generative neural networks that can obtain samples from the high-dimensional copula distribution without relying on parametric assumptions or the need to find a suitable tree structure.

Modeling Dependence Using Skew T Copulas: Bayesian Inference and Applications

A skew t copula is constructed from the skew t distribution of Sahu, Dey & Branco (2003) and substantially out-performs symmetric elliptical copula alternatives when coupled with Bayesian inference in two contemporary econometric studies.

Deep Archimedean Copulas

ACNet is introduced, a novel differentiable neural network architecture that enforces structural properties and enables one to learn an important class of copulas--Archimedean Copulas.

Statistical Inference Procedures for Bivariate Archimedean Copulas

Abstract A bivariate distribution function H(x, y) with marginals F(x) and G(y) is said to be generated by an Archimedean copula if it can be expressed in the form H(x, y) = ϕ–1[ϕ{F(x)} + ϕ{G(y)}]

Gaussian Process Vine Copulas for Multivariate Dependence

This paper discovers the latent functions that specify the shape of a conditional copula given its conditioning variables by following a Bayesian approach based on sparse Gaussian processes with expectation propagation for scalable, approximate inference.

Copula-like Variational Inference

This paper considers a new family of variational distributions motivated by Sklar's theorem. This family is based on new copula-like densities on the hypercube with non-uniform marginals which can be

Archimedean Copulas in High Dimensions: Estimators and Numerical Challenges Motivated by Financial Applications

The performance of known and new parametric estimators for the parameters of Archimedean copulas is investigated and related numerical difficulties are addressed and the numerical solutions developed extend to various asymmetric generalizations and important quantities such as distributions of radial parts or the Kendall distribution function.

The estimation of copulas : theory and practice

This chapter focuses on the practical issues practitioners are faced with, in particular concerning estimation and visualisation of copulas.