Search Results for author:
Found 10 papers, 1 papers with code
On Memorization and Privacy Risks of Sharpness Aware Minimization
In this work, we dissect these performance gains through the lens of data memorization in overparameterized models.
Risk-Adaptive Approaches to Stochastic Optimization: A Survey
Uncertainty is prevalent in engineering design, data-driven problems, and decision making broadly.
Optimizing Surveillance Satellites for the Synthetic Theater Operations Research Model
The Synthetic Theater Operations Research Model (STORM) simulates theater-level conflict and requires inputs about utilization of surveillance satellites to search large geographical areas.
On Robustness in Nonconvex Optimization with Application to Defense Planning
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.
Rockafellian Relaxation and Stochastic Optimization under Perturbations
We are also able to circumvent the fundamental difficulty in stochastic optimization that convergence of distributions fails to guarantee convergence of expectations.
Consistent Approximations in Composite Optimization
Approximations of optimization problems arise in computational procedures and sensitivity analysis.
Gradients and Subgradients of Buffered Failure Probability
Gradients and subgradients are central to optimization and sensitivity analysis of buffered failure probabilities.
Good and Bad Optimization Models: Insights from Rockafellians
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.
Certifiable Risk-Based Engineering Design Optimization
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
Diametrical Risk Minimization: Theory and Computations
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.
