Portfolio selection is difficult when the covariance structure of asset returns is unstable and only imperfectly predictable. In such settings, portfolios that rely heavily on the sample covariance matrix may become unstable and overly concentrated. This paper proposes a framework that uses transformed portfolio representations generated from shrinkage ideas to construct more stable portfolios with a minimum variance orientation. The method builds informative transformed dictionaries from shrinkage information and then selects portfolio exposures through sparse regularized optimization solved by an alternating direction method of multipliers algorithm. The approach is closely related to the Global Minimum Variance (GMV) portfolio, but avoids directly estimating a large number of shrinkage parameters. Rolling-window out-of-sample experiments on several asset universes show that the proposed portfolios often achieve stronger returns and better risk-adjusted performance than standard GMV, equal-weighted, and conventional shrinkage benchmarks in the considered sample. The results suggest that combining representations generated from shrinkage ideas with sparse coefficient regularization can improve portfolio stability under covariance uncertainty.
Sun, Ruili, Wang, Kunqi, Ma, Tiefeng et al. Portfolio selection based on shrinkage estimation of the covariance matrix and ADMM algorithm. // Journal of Asset Management. – 2026. – DOI: 10.1057/s41260-026-00468-w. – URL: http://link.springer.com/openurl/fulltext?id=doi:10.1057/s41260-026-00468-w
Sun, Ruili, Wang, Kunqi, Ma, Tiefeng, Liu, & Shuangzhe (2026). Portfolio selection based on shrinkage estimation of the covariance matrix and ADMM algorithm. Journal of Asset Management. https://doi.org/10.1057/s41260-026-00468-w
Sun, et al. “Portfolio selection based on shrinkage estimation of the covariance matrix and ADMM algorithm.” Journal of Asset Management, 2026. doi:10.1057/s41260-026-00468-w.
@article{Sun2026,
title = {Portfolio selection based on shrinkage estimation of the covariance matrix and ADMM algorithm},
author = {Sun and Ruili and Wang and Kunqi and Ma and Tiefeng and Liu and Shuangzhe},
journal = {Journal of Asset Management},
year = {2026},
doi = {10.1057/s41260-026-00468-w},
url = {http://link.springer.com/openurl/fulltext?id=doi:10.1057/s41260-026-00468-w}
}
Purpose Cultural intelligence (CQ) is associated with effectiveness in culturally diverse settings, yet capability development, coordinated action and organisational benefit require different explanations. This review examines the...
The main objective of this study is to examine stakeholder accountability in the case of the collapse of a public private partnership (PPP) service provider. Whilst PPPs have been embraced by governments across the globe to modernise...
Research on chief executive officers (CEOs) typically assumes that a single leader heads the firm, yet some firms divide this role among two or more co-CEOs. Drawing on an integrative review of 28 articles published between 2002 and...
A life insurer with a guaranteed crediting rate must earn that rate. Duration matching immunises the discounted value of the promise, which is a different object. Over June 2006–July 2026 a duration-matched general account missed a 4...
This study introduces an environmentally conscious supply chain inventory model for the cotton garment industry by integrating price, time-sensitive demand, advertising, seasonal or festival discounts, and greenness. The proposed model...