Statistical Learning Generalization Guarantees for Multifactor Stock Selection under Adversarial Distribution Shift

Yixuan  Liu

doi:10.54254/2753-8818/2026.29323

Theoretical and Natural ScienceOpen access

Statistical Learning Generalization Guarantees for Multifactor Stock Selection under Adversarial Distribution Shift

Research Article

Open Access

Statistical Learning Generalization Guarantees for Multifactor Stock Selection under Adversarial Distribution Shift

Yixuan Liu ^1*

¹ The Australian National University

^*Corresponding author: rara481846778@gmail.com

Published on 11 November 2025

TNS Vol.150

ISSN (Print): 2753-8826

ISSN (Online): 2753-8818

ISBN (Print): 978-1-80590-537-0

ISBN (Online): 978-1-80590-538-7

Download Cover

Abstract

The high volatility and non-stationarity of financial markets pose significant challenges to the application of traditional machine learning models in portfolio optimization and asset pricing. Under distributional shifts and extreme market conditions, these models often suffer from performance degradation and failure in risk control. Although existing studies have made progress in factor modeling and portfolio optimization, most approaches rely on the assumption of independent and identically distributed data or weak robustness constraints, leaving the problem of generalization under non-stationary and adversarial environments insufficiently addressed. To tackle this issue, this paper proposes a statistical learning generalization guarantee framework tailored to adversarial distributional shifts. The framework incorporates adversarial regularization into a multifactor deep neural network and derives PAC-Bayes generalization error bounds, thereby achieving consistency between theoretical guarantees and empirical robustness. Empirical experiments are conducted using high-frequency factor and trading data from the Chinese A-share market and the U.S. NYSE/NASDAQ market between 2015 and 2023. Three experimental settings, baseline model comparisons, adversarial perturbation simulations, and cross-market transfer evaluations, are designed. Results show that the proposed method significantly outperforms OLS regression, LASSO regression, and standard deep neural networks in key metrics such as annualized return, Sharpe ratio, and maximum drawdown, while also demonstrating stronger risk control through improvements in the Robustness Index. Further cross-market and temporal transfer experiments confirm the generalizability of the proposed model, proving its applicability not only in stable markets but also under extreme shocks, where it maintains return consistency and robustness.

Keywords:

Statistical Learning, Adversarial Distribution Shift, Multifactor Stock Selection, Portfolio Optimization, Generalization Guarantee

View PDF

References

[1]. Bhanot, Karan, et al. "Adversarial Auditing of Machine Learning Models under Compound Shift." European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. 2023.

[2]. Liang, T. (2024). Blessings and curses of covariate shifts: adversarial learning dynamics, directional convergence, and equilibria. Journal of Machine Learning Research, 25(140), 1-27.

[3]. Singh, H., Joshi, S., Doshi-Velez, F., & Lakkaraju, H. (2021). Learning under adversarial and interventional shifts. arXiv preprint arXiv: 2103.15933.

[4]. Liu, Jiashuo, et al. "Stable adversarial learning under distributional shifts." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 35. No. 10. 2021.

[5]. Vidot, Guillaume, et al. "A pac-bayes analysis of adversarial robustness." (2021).

[6]. Sabanayagam, Mahalakshmi, et al. "Generalization Certificates for Adversarially Robust Bayesian Linear Regression." arXiv preprint arXiv: 2502.14298 (2025).

[7]. Zhou, Sijia, Yunwen Lei, and Ata Kabán. "Randomized Pairwise Learning with Adaptive Sampling: A PAC-Bayes Analysis." arXiv preprint arXiv: 2504.02957 (2025).

[8]. Zhang, Yabin, et al. "Adversarial style augmentation for domain generalization." arXiv preprint arXiv: 2301.12643 (2023).

[9]. Liu, Jiashuo, et al. "Distributionally robust learning with stable adversarial training." IEEE Transactions on Knowledge and Data Engineering 35.11 (2022): 11288-11300.

[10]. Jin, Gaojie, et al. "Enhancing adversarial training with second-order statistics of weights." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022.

[11]. Ashtiani, Hassan, Vinayak Pathak, and Ruth Urner. "Simplifying Adversarially Robust PAC Learning with Tolerance." arXiv preprint arXiv: 2502.07232 (2025).