Algorithms for l₁-norm minimisation of index tracking error and their performance
Summary: The paper considers the index tracking problem with cardinality constraint and examines different methods for the numerical solution of the problem. Index tracking is a passive financial strategy that tries to replicate the performance of a given index or benchmark. The aim of investor is to find the weights of assets in her/his portfolio that minimise the tracking error, i.e., difference between the performance of the index and the portfolio. In this paper, we examine three different algorithms for index tracking error minimisation in \(l_{1}\)-norm (greedy algorithm, algorithm for \(l_{1}\)-norm minimisation with relaxation and differential evolution algorithm) and compare the empirical performance of the portfolios obtained by means of the algorithms.
- scientific article; zbMATH DE number 165316
- Cardinality versus \(q\)-norm constraints for index tracking
- Fast methods for the index tracking problem
- Simultaneous pursuit of out-of-sample performance and sparsity in index tracking portfolios
- A hybrid approach for index tracking with practical constraints
- Duality gap estimates for a class of greedy optimization algorithms in Banach spaces
- Robust and sparse portfolio model for index tracking
- Constrained Index Tracking under Loss Aversion Using Differential Evolution
- scientific article; zbMATH DE number 165316 (Why is no real title available?)
- Cardinality versus \(q\)-norm constraints for index tracking
- Simultaneous pursuit of out-of-sample performance and sparsity in index tracking portfolios
This page was built for publication: Algorithms for \(l_{1}\)-norm minimisation of index tracking error and their performance
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2204337)
