Research map / Learning theory and algorithms / Sample complexity
The Kelly Growth Optimal Portfolio with Ensemble Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add subset resampling inner loop to growth optimal portfolio (ablation) | GO · FF48 | Sharpe ratio: 0.43 -> 1.00 | Helped |
| add subset resampling inner loop to growth optimal portfolio (ablation) | GO · EQ181 | Sharpe ratio: 0.67 -> 1.34 | Helped |
| add bagging outer loop to growth optimal portfolio (ablation) | GO · FF25 | Sharpe ratio: 0.70 -> 0.71 | No clear effect |
| add bagging outer loop to growth optimal portfolio (ablation) | GO · EQ181 | Sharpe ratio: 0.67 -> 0.52 | Hurt |
| add bagging outer loop to growth optimal portfolio (ablation) | GO · ETF139 | Sharpe ratio: 1.33 -> 1.45 | Helped |
| add bagging outer loop on top of subset resampling (SS to EGO) (ablation) | SS · FF25 | Sharpe ratio: 1.09 -> 1.11 | Helped |
| add bagging outer loop on top of subset resampling (SS to EGO) (ablation) | SS · ETF139 | Sharpe ratio: 1.40 -> 1.45 | Helped |
| add bagging outer loop on top of subset resampling (SS to EGO) (ablation) | SS · EQ181 | Sharpe ratio: 1.34 -> 1.41 | Helped |
| ensemble (EGO) instead of plain growth optimal portfolio | GO · FF48 | Maximum drawdown (%): 76.15 -> 34.91 | Helped |
| ensemble (EGO) instead of plain growth optimal portfolio | GO · ETF139 | Maximum drawdown (%): 5.56 -> 2.02 | Helped |
| subset size n4 = n^0.7 versus n^0.5 or n^0.9 (ablation) | SS · simulation FF48 growth frontier | growth frontier | Helped |
| ensemble growth optimal vs equally-weighted portfolio | EW · EQ181 | Sharpe ratio: 0.97 -> 1.41 | Mixed |
Closest papers by meaning
- Latent Variable Estimation in Bayesian Black-Litterman Models (ICML 2025 · similarity 0.84)
- Autoregressive Policy Optimization for Constrained Allocation Tasks (NeurIPS 2024 · similarity 0.84)
- AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors (AAAI 2025 · similarity 0.83)
- AlphaQCM: Alpha Discovery in Finance with Distributional Reinforcement Learning (ICML 2025 · similarity 0.83)
- Automated Efficient Estimation using Monte Carlo Efficient Influence Functions (NeurIPS 2024 · similarity 0.83)
- DHMoE: Diffusion Generated Hierarchical Multi-Granular Expertise for Stock Prediction (AAAI 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.