Research map / Learning theory and algorithms / Combinatorial and search optimization
Learning the Efficient Frontier
Philippe Chatigny, Ivan Sergienko, Ryan Ferguson, Jordan Weir, Maxime Bergeron
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Replace numerical EF optimization with NeuralEF inference | EF optimization · EF throughput, A100 | evaluations/second: 111479.39 -> 343760.77 | Improved |
| Use FP16 instead of FP32 (ablation) | NeuralEF · EF throughput, A100 | evaluations/second: 128950.46 -> 343760.77 | Improved |
| Use FP16 instead of FP32 (ablation) | NeuralEF · EF accuracy | portfolio weight error: The paper reports FP32 and FP16 results in separate tables, without a direct paired delta. | No clear effect |
| Add dynamic greedy allocation rebalancing (DGAR) (ablation) | NeuralEF · EF test distribution | portfolio weight MAE | Improved |
| Add dynamic greedy allocation rebalancing (DGAR) (ablation) | NeuralEF · EF test distribution | constraint adherence optimality gap | Improved |
| Clean ambiguous optimization inputs before token projection (ablation) | NeuralEF · EF inputs with equivalent but ambiguously specified constraints | forecast accuracy | Improved |
| Remove input preprocessing (ablation) | NeuralEF · EF throughput, A100 | evaluations/second: 343760.77 -> 401641.81 | Improved |
| Remove input preprocessing (ablation) | NeuralEF · EF forecast accuracy on ambiguous inputs | forecast accuracy | Hurt |
| Use clean-only input preprocessing (ablation) | NeuralEF · EF throughput, A100 | evaluations/second: 343760.77 -> 366450.96 | Improved |
| Train and evaluate within the training input domain | NeuralEF · EF out-of-domain inputs | tail forecast accuracy | Improved |
Closest papers by meaning
- DFF: Decision-Focused Fine-Tuning for Smarter Predict-Then-Optimize with Limited Data (AAAI 2025 · similarity 0.82)
- Autoregressive Policy Optimization for Constrained Allocation Tasks (NeurIPS 2024 · similarity 0.82)
- AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors (AAAI 2025 · similarity 0.82)
- Adaptive-Gradient Policy Optimization: Enhancing Policy Learning in Non-Smooth Differentiable Simulations (ICML 2024 · similarity 0.81)
- BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning (NeurIPS 2024 · similarity 0.81)
- Overcoming the Optimizer's Curse: Obtaining Realistic Prescriptions from Neural Networks (ICML 2024 · similarity 0.81)
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.
