Complex risk is a critical factor for both intelligent systems and risk management. In this paper, we consider a special class of risk statistics, named complex risk statistics. Our result provides a new approach for addressing complex risk, especially in deep neural networks. By further developing the properties related to complex risk statistics, we are able to derive dual representation for such risk.
@article{arxiv.2003.09255,
title = {Complex risk statistics with scenario analysis},
author = {Fei Sun and Yichuan Dong},
journal= {arXiv preprint arXiv:2003.09255},
year = {2020}
}
Comments
arXiv admin note: text overlap with arXiv:1812.06185