Paper: arXiv 2408.07879
Authors: Chung-Han Hsieh, Jie-Ling Lu
Abstract
Solving large-scale robust portfolio optimization problems is challenging due to the high computational demands associated with an increasing number of assets, the amount of data considered, and market uncertainty. To address this issue, we propose an extended supporting hyperplane approximation approach for efficiently solving a class of distributionally robust portfolio problems for a general class of additively separable utility functions and polyhedral ambiguity distribution set, applied to a large-scale set of assets. Our technique is validated using a large-scale portfolio of the S&P 500 index constituents, demonstrating robust out-of-sample trading performance. More importantly, our empirical studies show that this approach significantly reduces computational time compared to traditional concave Expected Log-Growth (ELG) optimization, with running times decreasing from several thousand seconds to just a few. This method provides a scalable and practical solution to large-scale robust portfolio optimization, addressing both theoretical and practical challenges.
Complexity vs Empirical Score
- Math Complexity: 7.0/10
- Empirical Rigor: 8.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper employs advanced concepts from distributionally robust optimization, approximation theory, and convex analysis, though it abstracts away some derivation details; it is strongly validated with real-world S&P 500 data, demonstrating significant computational speedups and robust out-of-sample performance, making it both mathematically dense and empirically rigorous.
Research Flowchart
flowchart TD
A["Research Goal:<br>Efficient Large-Scale<br>Robust Portfolio Optimization"] --> B["Methodology:<br>Extended Supporting Hyperplane<br>Approximation Approach"]
B --> C["Data Input:<br>S&P 500 Constituents<br>High-Dimensional Dataset"]
C --> D["Computational Process:<br>Distributionally Robust<br>Optimization Solver"]
D --> E{"Comparison vs.<br>Traditional ELG Optimization"}
E -->|"Computational"| F["Outcome: Drastic Speedup<br>Time reduced from 1000s to few seconds"]
E -->|"Performance"| G["Outcome: Robust Out-of-Sample<br>Trading Performance"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes an extended supporting hyperplane approximation method for efficiently solving large-scale distributionally robust portfolio problems with additively separable utilities and polyhedral ambiguity sets, incorporating proportional transaction costs.
Source sentence
We propose an extended supporting hyperplane approximation approach for efficiently solving a class of distributionally robust portfolio problems for a general class of additively separable utility functions and polyhedral ambiguity distribution set, applied to a large-scale set of assets.
Assumes 3
- Asset returns are independent and identically distributed (i.i.d.) over time. model
Source sentence
Henceforth, we assume that the returns are independent and identically distributed (i.i.d.) over time t, but with some unknown joint distribution p with m supports.
- Turnover transaction costs are proportional with a fixed rate per asset, ci(t) ∈ [0,1). execution
Source sentence
For transaction costs, we consider a fixed rate charged on the turnover for the ith asset. Hence, the turnover transaction cost C(t) at period t is given by
- The ambiguous distribution set is polyhedral and contains the true return distribution. statistical
Source sentence
Consistent with Mohajerin Esfahani & Kuhn (2018); Li (2023); Hsieh (2024), we note that the random returns Xi are treated as independent and identically distributed (i.i.d.) samples from the true but unknown return distribution, which is assumed to lie within an ambiguous distribution set.
Data
S&P 500 constituents · equities
- S&P 500 constituent daily adjusted closing prices market-prices public
Source sentence
We use daily adjusted closing price data for S&P 500 constituent stocks from Yahoo! Finance (2024), covering three years from January 1, 2021, to December 31, 2023.
Costs
Modeled
Proportional turnover costs with cost vector ci(t) ∈[0,1) and turnover cost limits cmax (e.g., c·2L or c·L/2).
Source sentence
For transaction costs, we consider a fixed rate charged on the turnover for the ith asset.
Finds 3
Sharpe 1.36 (benchmark 0.29) · total return 10.3% · max drawdown 0.8%
- The extended hyperplane approximation reduces computational time from several thousand seconds to just a few seconds, achieving >99% speedup versus traditional ELG optimization. performance
Source sentence
Our empirical studies showed that the required running times decreased from several thousand seconds to just a few seconds even when the turnover costs and sliding window implementation are involved.
- The HYP approach runs in under 10 seconds per rebalance, compared to ELG runtimes of 5,000–9,000 seconds, while delivering comparable out‑of‑sample trading performance. performance
Source sentence
In the table, compared to the running time of ELG ranging from 5,000 to 9,000 seconds, the longest running time for our HYP approach is less than 10 seconds, significantly improving computational efficiency with the supporting hyperplane approximation.
- Robust out‑of‑sample trading performance is demonstrated on the S&P 500 portfolio, with cumulative returns and Sharpe ratios comparable to or better than benchmark buy‑and‑hold strategies. performance
Source sentence
Our technique is validated using a large‑scale portfolio of the S&P 500 index constituents, demonstrating robust out‑of‑sample trading performance.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 17 related papers). Coverage is partial, so this is neither replication nor refutation.
1 paper in the archive
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (57)
- On Joint Convexity of Trace Functions (2004)
- Global Portfolio Optimization (1992)
- Quantifying Distributional model risk via Optimal Rransport (2019)
- Distributionally Robust Optimization under Moment Uncertainty with Application to Data-Driven Problems (2010)
- Distributionally Robust Mean-Variance Portfolio Selection with Wasserstein Distances (2022)
- A Signal Processing Perspective on Financial Engineering (2016)
- On Adaptive Portfolio Management with Dynamic Black-Litterman Approach — → 2307.03391
- Introduction to Nonlinear Optimization: Theory, Algorithms, and Applications with Python and MATLAB (2023)
and 49 more
- Distributionally Robust Optimization: A Review (2019) — link
- Investment Science (2013)
- A Preference Foundation for Log Mean-Variance Criteria in Portfolio Choice Problems (1993)
- Value at Risk: the New Benchmark for Managing Financial Risk (2007)
- Contributions to the Theory of Kelly Betting with Applications to Stock Trading: A Control-Theoretic Approach (2019)
- The Kelly Capital Growth Investment Criterion: Theory and Practice (2011)
- Elements of Information Theory (2012)
- On Data-Driven Log-Optimal Portfolio: A Sliding Window Approach (2022)
- On Asymptotic Log-Optimal Portfolio Optimization (2023)
- Portfolio Selection: Efficient Diversification of Investments (1959)
- Impact of Error in Parameter Estimations on Large Scale Portfolio Optimization (2019)
- Portfolio Selection (1952)
- Large-Scale Portfolio Allocation under Transaction Costs and Model Uncertainty (2019)
- Optimization of Conditional Value-at-Risk (2000)
- An Overview of Value at Risk (1997)
- Large-Scale Minimum Variance Portfolio Allocation using Double Regularization (2020)
- Optimal portfolio management for engineering problems using nonconvex cardinality constraint: A computing perspective (2020)
- Large-Scale Portfolio Optimization (1984)
- Ambiguity in Asset Pricing and Portfolio Choice: A Review of the Literature (2010)
- A Review on Ambiguity in Stochastic Portfolio Optimization (2018)
- Cardinality-Constrained Distributionally Robust Portfolio Optimization (2023)
- The Markowitz Optimization Enigma: Is ``Optimized’’’ Optimal? (1989)
- An Interior Point Algorithm for Large Scale Portfolio Optimization (1993)
- Distributionally-Robust Optimization with Noisy Data for Discrete Uncertainties Using Total Variation Distance (2023)
- Large Scale Portfolio Optimization with Piecewise Linear Transaction Costs (2008)
- Convex Optimization (2004)
- Mean-Absolute Deviation Portfolio Optimization Model and its Applications to Tokyo Stock Market (1991)
- Pairs Trading under Transaction Costs using Model Predictive Control (2018)
- A Compact Mean-Variance-Skewness Model for Large-Scale Portfolio Optimization and Its Application to the NYSE Market (2007)
- Robust Growth-Optimal Portfolios (2016)
- Multi-Period Portfolio Optimization: Translation of Autocorrelation Risk to Excess Variance (2016)
- Distributional Robust Kelly Gambling: Optimal Strategy under Uncertainty in the Long-Run (2018) — link
- On Solving Robust Log-Optimal Portfolio: A Supporting Hyperplane Approximation Approach (2024)
- Wasserstein-Kelly Portfolios: A Robust Data-Driven Solution to Optimize Portfolio Growth — → 2302.13979
- A Robust Perspective on Transaction Costs in Portfolio Optimization (2018)
- Lectures on Stochastic Programming: Modeling and Theory (2021)
- Robust Portfolio Selection Problems: a Comprehensive Review (2022)
- Robust Portfolio Optimization and Management (2007)
- Yahoo! Finance (2024)
- Markowitz Revisited: Mean-Variance Models in Financial Portfolio Analysis (2001)
- Transaction Cost Optimization for Online Portfolio Selection (2018)
- A Data-Driven Approach to Multistage Stochastic Linear Optimization (2023)
- Value Function Gradient Learning for Large-Scale Multistage Stochastic Programming Problems (2023)
- CVX: Matlab Software for Disciplined Convex Programming, Version 2.1 (2014)
- CVXPY : A P ython-Embedded Modeling Language for Convex Optimization (2016) — link
- Data-Driven Distributionally Robust Optimization using the Wasserstein Metric: Performance Guarantees and Tractable Reformulations (2018)
- Small-Data, Large-Scale Linear Optimization with Uncertain Objectives (2021)
- A New Interpretation of Information Rate (1956)
- Linear Interpolation (1981)
2 of 57 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.