Conceitos Básicos
Proposing an end-to-end approach for Conditional Robust Optimization to enhance decision-making under uncertainty.
Estatísticas
"Recently, a risk sensitive variant of CO, known as Conditional Robust Optimization (CRO), combines uncertainty quantification with robust optimization."
"We propose a novel end-to-end approach to train a CRO model in a way that accounts for both the empirical risk of the prescribed decisions and the quality of conditional coverage of the contextual uncertainty set that supports them."
"We show empirically how our end-to-end learning approach outperforms other state-of-the-art methods on a portfolio optimization problem using the real world data from the US stock market."
Citações
"We propose for the first time an end-to-end training algorithm to produce contextual uncertainty sets that lead to reduced risk exposure for the solution of the down-stream CRO problem."
"Our contributions can be described as follows: We propose for the first time an end-to-end training algorithm to produce contextual uncertainty sets that lead to reduced risk exposure for the solution of the down-stream CRO problem."