Deep Declarative Risk Budgeting Portfolios

2025/04/28 by Manuel Parra-Diaz, Parra-Diaz, Manuel, Carlos Castro-Iragorri +1 · 1 voice · 1 citation
Computer Science · Decision Sciences · Economics, Econometrics and Finance · #Advanced Bandit Algorithms Research #Artificial neural network #Compromise #Computational Finance (q-fin.CP) #FOS: Economics and business #Implementation #Portfolio #Portfolio Management (q-fin.PM) #Project portfolio management #Risk and Portfolio Optimization #Risk management #Sensitivity (control systems) #Stability (learning theory) #Stochastic Gradient Optimization Techniques #q-fin.CP #q-fin.PM

paper · pdf · doi:10.48550/arxiv.2504.19980

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/04/28 · arxiv published 2025/04/28 · arxiv updated 2025/04/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Recent advances in deep learning have spurred the development of end-to-end frameworks for portfolio optimization that utilize implicit layers. However, many such implementations are highly sensitive to neural network initialization, undermining performance consistency. This research introduces a robust end-to-end framework tailored for risk budgeting portfolios that effectively reduces sensitivity to initialization. Importantly, this enhanced stability does not compromise portfolio performance, as our framework consistently outperforms the risk parity benchmark.

Citations

• Distributionally Robust End-to-End Portfolio Construction
• Data-driven integration of norm-penalized mean-variance portfolios
• A Universal End-to-End Approach to Portfolio Optimization via Deep Learning
• End-to-End Risk Budgeting Portfolio Optimization with Neural Networks
• Differentiable Convex Optimization Layers
• Constrained Risk Budgeting Portfolios: Theory, Algorithms, Applications & Puzzles
• Introduction to Risk Parity and Budgeting

Cited by

• Probability Bounding: Post-Hoc Calibration via Box-Constrained Softmax

Discussions

• Manuel Parra-Diaz, Carlos Castro-Iragorri: Deep Declarative Risk Budgeting Portfolios https://arxiv.org/abs/2504.19980 https://arxiv.org/pdf/2504.19980 https://arxiv.org/html/2504.19980 [bsky, 0 points, 1 comments]

Related

• End-to-End Risk Budgeting Portfolio Optimization with Neural Networks
• Financially Guided Deep Portfolio Optimization
• Deep Hedging to Manage Tail Risk
• Constrained Risk Budgeting Portfolios: Theory, Algorithms, Applications & Puzzles
• Neural Networks for Portfolio-Level Risk Management: Portfolio Compression, Static Hedging, Counterparty Credit Risk Exposures and Impact on Capital Requirement