Empirical risk minimization for risk-neutral composite optimal control with applications to bang-bang control
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914354417369088 |
|---|---|
| author | Milz, Johannes Walter, Daniel |
| author_facet | Milz, Johannes Walter, Daniel |
| contents | Nonsmooth composite optimization problems under uncertainty are prevalent in various scientific and engineering applications. We consider risk-neutral composite optimal control problems, where the objective function is the sum of a potentially nonconvex expectation function and a nonsmooth convex function. To approximate the risk-neutral optimization problems, we use a Monte Carlo sample-based approach, study its asymptotic consistency, and derive nonasymptotic sample size estimates. Our analyses leverage problem structure commonly encountered in PDE-constrained optimization problems, including compact embeddings and growth conditions. We apply our findings to bang-bang-type optimal control problems and propose the use of a conditional gradient method to solve them effectively. We present numerical illustrations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10384 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Empirical risk minimization for risk-neutral composite optimal control with applications to bang-bang control Milz, Johannes Walter, Daniel Optimization and Control Numerical Analysis 90C15, 90C59, 90C06, 35Q93, 49M41, 90C60 Nonsmooth composite optimization problems under uncertainty are prevalent in various scientific and engineering applications. We consider risk-neutral composite optimal control problems, where the objective function is the sum of a potentially nonconvex expectation function and a nonsmooth convex function. To approximate the risk-neutral optimization problems, we use a Monte Carlo sample-based approach, study its asymptotic consistency, and derive nonasymptotic sample size estimates. Our analyses leverage problem structure commonly encountered in PDE-constrained optimization problems, including compact embeddings and growth conditions. We apply our findings to bang-bang-type optimal control problems and propose the use of a conditional gradient method to solve them effectively. We present numerical illustrations. |
| title | Empirical risk minimization for risk-neutral composite optimal control with applications to bang-bang control |
| topic | Optimization and Control Numerical Analysis 90C15, 90C59, 90C06, 35Q93, 49M41, 90C60 |
| url | https://arxiv.org/abs/2408.10384 |