High-Dimensional Portfolio Selecton with Cardinality Constraints
This repo contains code for perform proximal gradient descent to solve sample average approximation of expected utility maximization problems with cardinality constraints.
We show that, under mild conditions, the $l_1$-regularized problem is equivalent to the $l_0$-constrained problem.
We use Python 3 for our code.
Please refer to
requirements.txt, and use
conda to create a virtual environment with required packages installed.