2021/02/17 by Ali Hasan, Hasan, Ali, Khalil Elkhalil +13 · 1 citation
Computer Science · Economics, Econometrics and Finance · Environmental Science · Mathematics · #Computation (stat.CO) #FOS: Computer and information sciences #Financial Risk and Volatility Modeling #Hydrology and Drought Analysis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Market Dynamics and Volatility #cs.LG #stat.CO #stat.ML
paper · pdf · doi:10.48550/arxiv.2102.09042
openalex publication_date 2021/02/17 · arxiv created 2022/03/01 · arxiv updated 2022/03/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose a novel neural network architecture that enables non-parametric calibration and generation of multivariate extreme value distributions (MEVs). MEVs arise from Extreme Value Theory (EVT) as the necessary class of models when extrapolating a distributional fit over large spatial and temporal scales based on data observed in intermediate scales. In turn, EVT dictates that d-max-decreasing, a stronger form of convexity, is an essential shape constraint in the characterization of MEVs. As far as we know, our proposed architecture provides the first class of non-parametric estimators for MEVs that preserve these essential shape constraints. We show that our architecture approximates the dependence structure encoded by MEVs at parametric rate. Moreover, we present a new method for sampling high-dimensional MEVs using a generative model. We demonstrate our methodology on a wide range of experimental settings, ranging from environmental sciences to financial mathematics and verify that the structural properties of MEVs are retained compared to existing methods.