End-to-End Conformal Calibration for Optimization Under Uncertainty
This addresses the challenge of obtaining calibrated uncertainty estimates for neural networks in high-dimensional decision-making, though it is incremental as it builds on existing conformal prediction and robust optimization methods.
The paper tackles the problem of ensuring robust decision-making under uncertainty by developing an end-to-end framework that learns uncertainty sets with conformal guarantees, improving performance in energy storage arbitrage and portfolio optimization applications.
Machine learning can significantly improve performance for decision-making under uncertainty across a wide range of domains. However, ensuring robustness guarantees requires well-calibrated uncertainty estimates, which can be difficult to achieve with neural networks. Moreover, in high-dimensional settings, there may be many valid uncertainty estimates, each with its own performance profile - i.e., not all uncertainty is equally valuable for downstream decision-making. To address this problem, this paper develops an end-to-end framework to learn uncertainty sets for conditional robust optimization in a way that is informed by the downstream decision-making loss, with robustness and calibration guarantees provided by conformal prediction. In addition, we propose to represent general convex uncertainty sets with partially input-convex neural networks, which are learned as part of our framework. Our approach consistently improves upon two-stage estimate-then-optimize baselines on concrete applications in energy storage arbitrage and portfolio optimization.