| Speaker: Andy Philpott Affiliation: University of Auckland (Department of Engineering Science) Time: 2pm Friday, 21 May, 2021 Location: Clock Tower 039 (105S-039) |
| We consider stochastic optimization problems in which we aim to minimize the expected value of an objective function with respect to an unknown distribution of random parameters. We analyse the out-ofsample performance of solutions obtained by solving a distributionally robust version of the sample average approximation problem for unconstrained quadratic problems, and derive conditions under which these solutions are improved in comparison with those of the sample average approximation. We compare different mechanisms for constructing a robust solution: phi-divergence using both total variation, standard smooth phi functions and a CVaR-based risk measure. (joint work with Eddie Anderson, University of Sydney and Imperial College) |