Date: October, 4th, 14H30
Place: Inria Lille-Nord Europe
Abstract: Uncertainty in classical stochastic programming models is often described solely by independent random parameters, ignoring their dependence on multidimensional features. We propose a novel contextual chance-constrained programming formulation that incorporates features and argue that a solution that ignores them may not be implementable. We show the exponential convergence of our scheme as the number of data points increases. We illustrate our findings with a prescriptive portfolio problem that includes real-world features processed through Principal Feature Analysis.
This is joint work with H. Rahimian (Clemson University, United States), Domingo Ramírez (PUC-Chile), Arturo Cifuentes (PUC-Chile).
