SMGO: a set membership approach to data-driven global optimization
From MaRDI portal
(Redirected from SMGO: a set membership approach to data-driven global optimization)
Abstract: Many science and engineering applications feature non-convex optimization problems where the objective function can not be handled analytically, i.e. it is a black box. Examples include design optimization via experiments, or via costly finite elements simulations. To solve these problems, global optimization routines are used. These iterative techniques must trade-off exploitation close to the current best point with exploration of unseen regions of the search space. In this respect, a new global optimization strategy based on a Set Membership (SM) framework is proposed. Assuming Lipschitz continuity of the cost function, the approach employs SM concepts to decide whether to switch from an exploitation mode to an exploration one, and vice-versa. The resulting algorithm, named SMGO (Set Membership Global Optimization) is presented. Theoretical properties regarding convergence and computational complexity are derived, and implementation aspects are discussed. Finally, the SMGO performance is evaluated on a set of benchmark non-convex problems and compared with those of other global optimization approaches.
Recommendations
- Efficient global optimization of expensive black-box functions
- Continuous global optimization through the generation of parametric curves
- A simplicial homology algorithm for Lipschitz optimisation
- Global continuous optimization with error bound and fast convergence
- Learning Global Optimization Through a Support Vector Machine Based Adaptive Multistart Strategy
Cites work
- A peak-over-threshold search method for global optimization
- A Sequential Method Seeking the Global Maximum of a Function
- Additive scaling and the \texttt{DIRECT} algorithm
- An algorithm for finding the absolute extremum of a function
- Best practices for comparing optimization algorithms
- Computation of local radius of information in SM-IBC identification of nonlinear systems
- Direct Filtering: A New Approach to Optimal Filter Design for Nonlinear Systems
- Efficient global optimization of expensive black-box functions
- Global optimization via inverse distance weighting and radial basis functions
- Globally-biased disimpl algorithm for expensive global optimization
- Lipschitzian optimization without the Lipschitz constant
- Multidimensional global extremum seeking via the DIRECT optimisation algorithm
- Set membership identification of nonlinear systems
- Simplicial Lipschitz optimization without the Lipschitz constant
- Unified set membership theory for identification, prediction and filtering of nonlinear systems
- UOBYQA: unconstrained optimization by quadratic approximation
Cited in
(4)- Global continuous optimization with error bound and fast convergence
- SMGO-\(\Delta\): balancing caution and reward in global optimization with black-box constraints
- Data-driven Lipschitz-informed convex underestimators for branch-and-bound optimization of black-box functions
- \texttt{DATA-DRIVEN PRONTO}: a model-free solution for numerical optimal control
This page was built for publication: SMGO: a set membership approach to data-driven global optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2065241)
