Research map / Probabilistic and scientific modeling / Molecules and proteins
Task-based End-to-end Model Learning in Stochastic Optimization
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 |
|---|---|---|---|
| train forecaster end-to-end on downstream stochastic programming task loss instead of RMSE | load forecasting NN · Generator scheduling | task loss: 38.6% | Helped |
| task-based loss instead of cost-weighted RMSE | load forecasting NN · Generator scheduling | task loss: 8.6% | Helped |
| task-based loss instead of RMSE | load forecasting NN · Generator scheduling | RMSE | Hurt |
| task-based loss instead of RMSE | price forecasting NN · Battery storage | task loss: 131 ± 145 -> 95.9 ± 29.8 | No clear effect |
| task-based learning instead of MLE when the model is misspecified | linear model · Synthetic inventory (nonlinear true model) | cost | Helped |
| task-based learning instead of MLE when the model is correctly specified | linear model · Synthetic inventory (linear true model) | cost | Hurt |
| task-based model instead of pure end-to-end policy network | inventory stock · Synthetic inventory | cost | Helped |
Closest papers by meaning
- End-to-End Learning for Stochastic Optimization: A Bayesian Perspective (ICML 2023 · similarity 0.89)
- The Perils of Learning Before Optimizing (AAAI 2022 · similarity 0.86)
- E2E-AT: A Unified Framework for Tackling Uncertainty in Task-Aware End-to-End Learning (AAAI 2024 · similarity 0.84)
- Leaving the Nest: Going beyond Local Loss Functions for Predict-Then-Optimize (AAAI 2024 · similarity 0.82)
- Joint Learning of Energy-based Models and their Partition Function (ICML 2025 · similarity 0.82)
- Neural Combinatorial Optimization for Stochastic Flexible Job Shop Scheduling Problems (AAAI 2025 · similarity 0.82)
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.