{"ID":5551830,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T08:00:54.702513071Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00581","arxiv_id":"2607.00581","title":"Decision-focused Sparse Tangent Portfolio Optimization","abstract":"Sparse tangent portfolio optimization aims to learn an interpretable, low-cardinality portfolio in the tangency direction of the mean-variance frontier. However, the associated cardinality-constrained formulation is NP-hard, and standard predict-then-optimize pipelines often misalign forecasting accuracy with downstream portfolio quality. We propose an end-to-end decision-focused learning framework that reformulates Sharpe ratio maximization as a Disciplined Parametrized Programming (DPP)-compliant convex programming layer and replaces discrete selection with a smooth top-$k$ operator enforcing an exact cardinality $k$. This enables gradient flow through prediction, asset selection, and re-optimization, allowing the predictive model to directly optimize portfolio performance. Across four major equity markets, our method achieves competitive and often superior out-of-sample Sharpe ratios compared with historical and prediction-focused baselines, with particularly strong gains in larger asset universes. Our \\href{https://github.com/feuerwerksh/Diffble-card-SR}{code} is publicly available.","short_abstract":"Sparse tangent portfolio optimization aims to learn an interpretable, low-cardinality portfolio in the tangency direction of the mean-variance frontier. However, the associated cardinality-constrained formulation is NP-hard, and standard predict-then-optimize pipelines often misalign forecasting accuracy with downstrea...","url_abs":"https://arxiv.org/abs/2607.00581","url_pdf":"https://arxiv.org/pdf/2607.00581v1","authors":"[\"Haeun Jeon\",\"Seunghoon Choi\",\"Hyunglip Bae\",\"Yongjae Lee\",\"Woo Chang Kim\"]","published":"2026-07-01T08:06:07Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":613846,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-02T01:54:51.863792489Z","DeletedAt":null,"paper_id":5551830,"paper_url":"https://arxiv.org/abs/2607.00581","paper_title":"Decision-focused Sparse Tangent Portfolio Optimization","repo_url":"https://github.com/feuerwerksh/Diffble-card-SR","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}