Neural Nonlinear Shrinkage of Covariance Matrices for Minimum Variance Portfolio Optimization

• URL: http://arxiv.org/abs/2601.15597v1
• Date: Thu, 22 Jan 2026 02:44:33 GMT
• Title: Neural Nonlinear Shrinkage of Covariance Matrices for Minimum Variance Portfolio Optimization
• Authors: Liusha Yang, Siqi Zhao, Shuqi Chai,
• Abstract summary: It is a hybrid approach that integrates statistical estimation with machine learning.<n> Empirical results on stock daily returns from Standard & Poor's 500 Index (S&P500) demonstrate that the proposed method consistently achieves lower out-of-sample realized risk.
• Score: 1.2001699611848735
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This paper introduces a neural network-based nonlinear shrinkage estimator of covariance matrices for the purpose of minimum variance portfolio optimization. It is a hybrid approach that integrates statistical estimation with machine learning. Starting from the Ledoit-Wolf (LW) shrinkage estimator, we decompose the LW covariance matrix into its eigenvalues and eigenvectors, and apply a lightweight transformer-based neural network to learn a nonlinear eigenvalue shrinkage function. Trained with portfolio risk as the loss function, the resulting precision matrix (the inverse covariance matrix) estimator directly targets portfolio risk minimization. By conditioning on the sample-to-dimension ratio, the approach remains scalable across different sample sizes and asset universes. Empirical results on stock daily returns from Standard & Poor's 500 Index (S&P500) demonstrate that the proposed method consistently achieves lower out-of-sample realized risk than benchmark approaches. This highlights the promise of integrating structural statistical models with data-driven learning.

Related papers

• A Simplified Analysis of SGD for Linear Regression with Weight Averaging [64.2393952273612]
  Recent work bycitetzou 2021benign provides sharp rates for SGD optimization in linear regression using constant learning rate.<n>We provide a simplified analysis recovering the same bias and variance bounds provided incitepzou 2021benign based on simple linear algebra tools.<n>We believe our work makes the analysis of gradient descent on linear regression very accessible and will be helpful in further analyzing mini-batching and learning rate scheduling.
  arXiv  Detail & Related papers  (2025-06-18T15:10:38Z)
• Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems [53.03951222945921]
  We analyze smoothed (perturbed) policies, adding controlled random perturbations to the direction used by the linear oracle.<n>Our main contribution is a generalization bound that decomposes the excess risk into perturbation bias, statistical estimation error, and optimization error.<n>We illustrate the scope of the results on applications such as vehicle scheduling, highlighting how smoothing enables both tractable training and controlled generalization.
  arXiv  Detail & Related papers  (2024-07-24T12:00:30Z)
• Meta-Learning with Generalized Ridge Regression: High-dimensional Asymptotics, Optimality and Hyper-covariance Estimation [14.194212772887699]
  We consider meta-learning within the framework of high-dimensional random-effects linear models. We show the precise behavior of the predictive risk for a new test task when the data dimension grows proportionally to the number of samples per task. We propose and analyze an estimator inverse random regression coefficients based on data from the training tasks.
  arXiv  Detail & Related papers  (2024-03-27T21:18:43Z)
• On the design-dependent suboptimality of the Lasso [27.970033039287884]
  We show that the Lasso estimator is provably minimax rate-suboptimal when the minimum singular value is small. Our lower bound is strong enough to preclude the sparse statistical optimality of all forms of the Lasso.
  arXiv  Detail & Related papers  (2024-02-01T07:01:54Z)
• Self-Supervised Dataset Distillation for Transfer Learning [77.4714995131992]
  We propose a novel problem of distilling an unlabeled dataset into a set of small synthetic samples for efficient self-supervised learning (SSL) We first prove that a gradient of synthetic samples with respect to a SSL objective in naive bilevel optimization is textitbiased due to randomness originating from data augmentations or masking. We empirically validate the effectiveness of our method on various applications involving transfer learning.
  arXiv  Detail & Related papers  (2023-10-10T10:48:52Z)
• Forecasting Large Realized Covariance Matrices: The Benefits of Factor Models and Shrinkage [1.0323063834827415]
  We decompose the return covariance matrix using standard firm-level factors and use sectoral restrictions in the residual covariance matrix. Our methodology improves forecasting precision relative to standard benchmarks and leads to better estimates of minimum variance portfolios.
  arXiv  Detail & Related papers  (2023-03-22T16:38:22Z)
• Learning Graphical Factor Models with Riemannian Optimization [70.13748170371889]
  This paper proposes a flexible algorithmic framework for graph learning under low-rank structural constraints. The problem is expressed as penalized maximum likelihood estimation of an elliptical distribution. We leverage geometries of positive definite matrices and positive semi-definite matrices of fixed rank that are well suited to elliptical models.
  arXiv  Detail & Related papers  (2022-10-21T13:19:45Z)
• Deep Learning Based Residuals in Non-linear Factor Models: Precision Matrix Estimation of Returns with Low Signal-to-Noise Ratio [0.0]
  This paper introduces a consistent estimator and rate of convergence for the precision matrix of asset returns in large portfolios. Our estimator remains valid even in low signal-to-noise ratio environments typical for financial markets.
  arXiv  Detail & Related papers  (2022-09-09T20:29:54Z)
• Learning to Estimate Without Bias [57.82628598276623]
  Gauss theorem states that the weighted least squares estimator is a linear minimum variance unbiased estimation (MVUE) in linear models. In this paper, we take a first step towards extending this result to non linear settings via deep learning with bias constraints. A second motivation to BCE is in applications where multiple estimates of the same unknown are averaged for improved performance.
  arXiv  Detail & Related papers  (2021-10-24T10:23:51Z)
• Understanding Implicit Regularization in Over-Parameterized Single Index Model [55.41685740015095]
  We design regularization-free algorithms for the high-dimensional single index model. We provide theoretical guarantees for the induced implicit regularization phenomenon.
  arXiv  Detail & Related papers  (2020-07-16T13:27:47Z)
• Covariance Estimation for Matrix-valued Data [9.739753590548796]
  We propose a class of distribution-free regularized covariance estimation methods for high-dimensional matrix data. We formulate a unified framework for estimating bandable covariance, and introduce an efficient algorithm based on rank one unconstrained Kronecker product approximation. We demonstrate the superior finite-sample performance of our methods using simulations and real applications from a gridded temperature anomalies dataset and a S&P 500 stock data analysis.
  arXiv  Detail & Related papers  (2020-04-11T02:15:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.