66. Cardinality-Constrained Optimization for Large-Scale Portfolio
Invited abstract in session MB-13: True sparsity in Standard Quadratic Problems, stream Sparsity guarantee and cardinality-constrained (MI)NLPs.
Monday, 10:30-12:30Room: B100/6009
Authors (first author is the speaker)
| 1. | Yuan Chen
|
| Department of Statistics and Operations Research, University of Wien | |
| 2. | Immanuel Bomze
|
| Dept. of Statistics and OR, University of Vienna | |
| 3. | Nikolaus Hautsch
|
| Department of Statistics and Operations Research, University of Vienna | |
| 4. | Bo Peng
|
| University of Vienna |
Abstract
We propose a portfolio optimization model that reconciles Keynes's advocacy for concentrated investments with Markowitz's emphasis on diversification. By incorporating cardinality constraints into the Markowitz mean-variance framework, we enable investors to focus on a small set of assets, fostering specialized expertise. Cardinality constraints allow investors to still use the sample covariance matrix in high-dimensional settings with limited data, balancing diversification needs while mitigating estimation errors inherent in such environments.
Keywords
- Nonlinear mixed integer optimization
- Complementarity and variational problems
- Optimization in industry, business and finance
Status: accepted
Back to the list of papers