End-to-End Large Portfolio Optimization for Variance Minimization with Neural Networks through Covariance Cleaning

ArXi:2507.01918v3 Announce Type: replace-cross We develop a rotation-invariant neural network that provides the global minimum-variance portfolio by jointly learning how to lag-transform historical returns and marginal volatilities and how to regularise the eigenvalues of large equity covariance matrices. This explicit mathematical mapping offers clear interpretability of each module's role, so the model cannot be regarded as a pure black box.