Research map / Learning theory and algorithms / Prediction and decision losses
Risk Bounds and Calibration for a Smart Predict-then-Optimize Method
Heyuan Liu, Paul Grigas
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 |
|---|---|---|---|
| Train with SPO+ instead of squared ℓ2 prediction error | Portfolio allocation · Portfolio allocation, larger polynomial degrees, neural network | normalized test set SPO loss | Improved |
| Train with SPO instead of SPO+ | Portfolio allocation · Portfolio allocation, larger polynomial degrees, neural network | normalized test set SPO loss | Improved |
| Train with ℓ1 instead of squared ℓ2 prediction error | Portfolio allocation · Portfolio allocation | normalized test set SPO loss | Improved |
| Add a log-barrier constraint to the feasible region used to form the SPO+ surrogate (ablation) | SPO+ for cost-sensitive multi-class classification · Cost-sensitive multi-class classification, small training sets | test set SPO loss | Improved |
| Add a log-barrier constraint to the feasible region used to form the SPO+ surrogate (ablation) | SPO+ for cost-sensitive multi-class classification · Cost-sensitive multi-class classification, large training sets | test set SPO loss | Hurt |
| Use regular SPO+ instead of the log-barrier feasible-region approximation (ablation) | SPO+ for cost-sensitive multi-class classification · Cost-sensitive multi-class classification, large training sets | test set SPO loss | Improved |
Closest papers by meaning
- Smart Surrogate Losses for Contextual Stochastic Linear Optimization with Robust Constraints (NeurIPS 2025 · similarity 0.89)
- Efficient Stochastic Approximation of Minimax Excess Risk Optimization (ICML 2024 · similarity 0.87)
- Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel–Young Losses (NeurIPS 2025 · similarity 0.87)
- Non-Asymptotic and Non-Lipschitzian Bounds on Optimal Values in Stochastic Optimization Under Heavy Tails (ICML 2025 · similarity 0.87)
- Small-loss Adaptive Regret for Online Convex Optimization (ICML 2024 · similarity 0.86)
- Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss (NeurIPS 2024 · similarity 0.86)
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.
