Research map / Bandits and online learning / Online convex optimization and games
Online Decision-Focused Learning
Aymeric Capitaine, Maxime Haddouche, Eric Moulines, Michael I. Jordan, Etienne Boursier, Alain Oliviero Durmus
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 |
|---|---|---|---|
| use decision-focused online learning (DF-OGD, DF-FTPL) instead of prediction-focused OGD | online linear cost predictor · synthetic online knapsack (K=5, T=5000, misspecified model) | average cumulated decision cost | Improved |
| use decision-focused online learning instead of prediction-focused OGD | online linear cost predictor · synthetic online knapsack (K=5, T=5000) | prediction MSE | Hurt |
| use DF-OGD and DF-FTPL instead of online SPO | online linear cost predictor · synthetic online knapsack (K=5, T=5000) | average cumulated decision cost | Improved |
| increase model misspecification (gamma from 0 to 1) (ablation) | DF-OGD versus PF-OGD · synthetic interpolated linear/nonlinear costs (T=1000, 50 runs) | cumulated cost gap PFL minus DFL | Improved |
| scale to 80 items | DF-OGD and DF-FTPL · synthetic online knapsack (K=80) | average cumulated decision cost | Improved |
Closest papers by meaning
- Online Decision-Focused Learning under Semi-Bandit Feedback (NeurIPS 2026 · similarity 0.92)
- Solver-Free Decision-Focused Learning for Linear Optimization Problems (NeurIPS 2025 · similarity 0.90)
- DFF: Decision-Focused Fine-Tuning for Smarter Predict-Then-Optimize with Limited Data (AAAI 2025 · similarity 0.88)
- Feasibility-Aware Decision-Focused Learning for Predicting Parameters in the Constraints (NeurIPS 2025 · similarity 0.87)
- Locally Convex Global Loss Network for Decision-Focused Learning (AAAI 2025 · similarity 0.87)
- Leaving the Nest: Going beyond Local Loss Functions for Predict-Then-Optimize (AAAI 2024 · similarity 0.85)
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.
