# Risk Bounds and Calibration for a Smart Predict-then-Optimize Method

arXiv: https://arxiv.org/abs/2108.08887 · HTML: https://mlsanity.com/paper/2108.08887/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 19 Aug 2021.

## Builds on (most cited first, 8 of 8)

- [Smart "Predict, then Optimize"](https://mlsanity.com/paper/1710.08005/) (2017)
- [End-to-End Constrained Optimization Learning: A Survey](https://mlsanity.com/paper/2103.16378/) (2021)
- [From Predictive to Prescriptive Analytics](https://mlsanity.com/paper/1402.5481/) (2014)
- [A vector-contraction inequality for Rademacher complexities](https://mlsanity.com/paper/1605.00251/) (2016)
- [Generalization Bounds in the Predict-then-Optimize Framework](https://mlsanity.com/paper/1905.11488/) (2019)
- [Fast Rates for Contextual Linear Optimization](https://mlsanity.com/paper/2011.03030/) (2020)
- [On Structured Prediction Theory with Calibrated Convex Surrogate Losses](https://mlsanity.com/paper/1703.02403/) (2017)
- [Risk Guarantees for End-to-End Prediction and Optimization Processes](https://mlsanity.com/paper/2012.15046/) (2020)

## Built on by (most cited first, 29 of 29)

- [Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities](https://mlsanity.com/paper/2307.13565/) (2023)
- [A Survey of Contextual Optimization Methods for Decision Making under Uncertainty](https://mlsanity.com/paper/2306.10374/) (2023)
- [High-Dimensional Prediction for Sequential Decision Making](https://mlsanity.com/paper/2310.17651/) (2023)
- [Integrated Conditional Estimation-Optimization](https://mlsanity.com/paper/2110.12351/) (2021)
- [SurCo: Learning Linear Surrogates For Combinatorial Nonlinear Optimization Problems](https://mlsanity.com/paper/2210.12547/) (2022)
- [Estimate-Then-Optimize versus Integrated-Estimation-Optimization versus Sample Average Approximation: A Stochastic Dominance Perspective](https://mlsanity.com/paper/2304.06833/) (2023)
- [End-to-end Learning for Fair Ranking Systems](https://mlsanity.com/paper/2111.10723/) (2021)
- [Decision-Focused Learning with Directional Gradients](https://mlsanity.com/paper/2402.03256/) (2024)
- [Maximum Optimality Margin: A Unified Approach for Contextual Linear Programming and Inverse Linear Programming](https://mlsanity.com/paper/2301.11260/) (2023)
- [Online Contextual Decision-Making with a Smart Predict-then-Optimize Method](https://mlsanity.com/paper/2206.07316/) (2022)
- [Dissecting the Impact of Model Misspecification in Data-driven Optimization](https://mlsanity.com/paper/2503.00626/) (2025)
- [Expert-Calibrated Learning for Online Optimization with Switching Costs](https://mlsanity.com/paper/2204.08572/) (2022)
- [A Note on Task-Aware Loss via Reweighing Prediction Loss by Decision-Regret](https://mlsanity.com/paper/2211.05116/) (2022)
- [Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees](https://mlsanity.com/paper/2306.00172/) (2023)
- [Robustified Learning for Online Optimization with Memory Costs](https://mlsanity.com/paper/2305.00677/) (2023)
- [GenCO: Generating Diverse Designs with Combinatorial Constraints](https://mlsanity.com/paper/2310.02442/) (2023)
- [A Solver-Free Training Method for Predict-then-Optimize](https://mlsanity.com/paper/2606.19587/) (2026)
- [Data Depth as a Risk](https://mlsanity.com/paper/2507.08518/) (2025)
- [Solve Smart, Not Often: Policy Learning for Costly MILP Re-solving](https://mlsanity.com/paper/2509.23470/) (2025)
- [Decision-Focused Federated Learning Under Heterogeneous Objectives and Constraints](https://mlsanity.com/paper/2604.20031/) (2026)
- [Decision-Focused On-Policy Learning for Contextual Linear Optimization with Partial Feedback](https://mlsanity.com/paper/2606.01081/) (2026)
- [Smart Predict-then-Optimize Method with Dependent Data: Risk Bounds and Calibration of Autoregression](https://mlsanity.com/paper/2411.12653/) (2024)
- [Timing is Important: Risk-aware Fund Allocation based on Time-Series Forecasting](https://mlsanity.com/paper/2505.24835/) (2025)
- [Decision-focused Sensing and Forecasting for Adaptive and Rapid Flood Response: An Implicit Learning Approach](https://mlsanity.com/paper/2510.16015/) (2025)
- [Smooth Learning with Hard Constraints via Legendre-Regularized Policies](https://mlsanity.com/paper/2607.24007/) (2026)
- [When Do Surrogate Updates Improve Decisions? A Local Theory of Trajectory-Wise Transfer](https://mlsanity.com/paper/2608.01130/) (2026)
- [Deciding When to Decide: Testing Operational Suboptimality Under Distributional Shift](https://mlsanity.com/paper/2608.29465/) (2026)
- [Geometric Identification in Predict-Then-Optimize Learning](https://mlsanity.com/paper/2609.33472/) (2026)
- [Largest Rashomon sets of decision trees for robust contextual optimization](https://mlsanity.com/paper/2610.04385/) (2026)

## Abstract (arXiv)

The predict-then-optimize framework is fundamental in practical stochastic decision-making problems: first predict unknown parameters of an optimization model, then solve the problem using the predicted values. A natural loss function in this setting is defined by measuring the decision error induced by the predicted parameters, which was named the Smart Predict-then-Optimize (SPO) loss by Elmachtoub and Grigas [arXiv:1710.08005]. Since the SPO loss is typically nonconvex and possibly discontinuous, Elmachtoub and Grigas [arXiv:1710.08005] introduced a convex surrogate, called the SPO+ loss, that importantly accounts for the underlying structure of the optimization model. In this paper, we greatly expand upon the consistency results for the SPO+ loss provided by Elmachtoub and Grigas [arXiv:1710.08005]. We develop risk bounds and uniform calibration results for the SPO+ loss relative to the SPO loss, which provide a quantitative way to transfer the excess surrogate risk to excess true risk. By combining our risk bounds with generalization bounds, we show that the empirical minimizer of the SPO+ loss achieves low excess true risk with high probability. We first demonstrate these results in the case when the feasible region of the underlying optimization problem is a polyhedron, and then we show that the results can be strengthened substantially when the feasible region is a level set of a strongly convex function. We perform experiments to empirically demonstrate the strength of the SPO+ surrogate, as compared to standard ℓ1 and squared ℓ2 prediction error losses, on portfolio allocation and cost-sensitive multi-class classification problems.