Deep Generative Quantile-Copula Models for Probabilistic Forecasting
This addresses the problem of accurate multivariate probabilistic forecasting for applications like finance or weather, representing an incremental improvement by integrating existing concepts into a novel framework.
The paper tackles multivariate probabilistic forecasting by introducing a new category of generative models that combine quantile functions and copulas, achieving performance and versatility in time series tasks.
We introduce a new category of multivariate conditional generative models and demonstrate its performance and versatility in probabilistic time series forecasting and simulation. Specifically, the output of quantile regression networks is expanded from a set of fixed quantiles to the whole Quantile Function by a univariate mapping from a latent uniform distribution to the target distribution. Then the multivariate case is solved by learning such quantile functions for each dimension's marginal distribution, followed by estimating a conditional Copula to associate these latent uniform random variables. The quantile functions and copula, together defining the joint predictive distribution, can be parameterized by a single implicit generative Deep Neural Network.