no code implementations • 30 Sep 2023 • Young In Kim, Pratiksha Agrawal, Johannes O. Royset, Rajiv Khanna
In this work, we dissect these performance gains through the lens of data memorization in overparameterized models.
no code implementations • 1 Dec 2022 • Johannes O. Royset
Uncertainty is prevalent in engineering design, data-driven problems, and decision making broadly.
no code implementations • 20 Oct 2022 • Steven M. Warner, Johannes O. Royset
The Synthetic Theater Operations Research Model (STORM) simulates theater-level conflict and requires inputs about utilization of surveillance satellites to search large geographical areas.
no code implementations • 20 Aug 2022 • Johannes O. Royset
In the context of structured nonconvex optimization, we estimate the increase in minimum value for a decision that is robust to parameter perturbations as compared to the value of a nominal problem.
no code implementations • 10 Apr 2022 • Johannes O. Royset, Louis L. Chen, Eric Eckstrand
We are also able to circumvent the fundamental difficulty in stochastic optimization that convergence of distributions fails to guarantee convergence of expectations.
no code implementations • 13 Jan 2022 • Johannes O. Royset
Approximations of optimization problems arise in computational procedures and sensitivity analysis.
no code implementations • 12 Sep 2021 • Johannes O. Royset, Ji-Eun Byun
Gradients and subgradients are central to optimization and sensitivity analysis of buffered failure probabilities.
no code implementations • 13 May 2021 • Johannes O. Royset
The tuning of these alternative problems turns out to be intimately tied to finding multipliers in optimality conditions and thus emerges as a main component of several optimization algorithms.
no code implementations • 13 Jan 2021 • Anirban Chaudhuri, Boris Kramer, Matthew Norton, Johannes O. Royset, Karen Willcox
CRiBDO is contrasted with reliability-based design optimization (RBDO), where uncertainties are accounted for via the probability of failure, through a structural and a thermal design problem.
Optimization and Control Computational Engineering, Finance, and Science Data Analysis, Statistics and Probability Computation
1 code implementation • 24 Oct 2019 • Matthew Norton, Johannes O. Royset
The theoretical and empirical performance of Empirical Risk Minimization (ERM) often suffers when loss functions are poorly behaved with large Lipschitz moduli and spurious sharp minimizers.