Neural Inference Functions for Margins for Time Series Copula Models

TL;DR

This paper introduces N-IFM, a neural-network-based framework for fast and efficient parameter estimation in copula models for multivariate time series, outperforming traditional methods in computational speed while maintaining accuracy.

Contribution

The paper presents a novel neural inference framework for copula models, enabling rapid parameter estimation and model comparison in multivariate time series analysis.

Findings

N-IFM achieves substantial computational speedups over Hamiltonian Monte Carlo.

N-IFM maintains comparable inferential accuracy to traditional Bayesian methods.

The approach is validated on both simulated and real datasets.

Abstract

Copula models are widely employed in multivariate time series analysis because they permit flexible modelling of marginal distributions independently of the dependence structure, which is fully characterised by the copula function. However, Bayesian inference with these models becomes computationally demanding as the number of variables in the time series increases. Motivated by the classical inference functions for margins (IFM) approach, we propose a new neural-network based inference framework for estimating parameters in copula models, termed the neural inference functions for margins (N-IFM). N-IFM enables rapid parameter estimation for new data, fast sequential prediction, and efficient model comparison via time-series validation. We assess the performance of N-IFM using both simulated and real datasets and compare it to Hamiltonian Monte Carlo, demonstrating substantial computational gains with comparable inferential accuracy.