# Decision-aware training of spatiotemporal forecasting models to select a top K subset of sites for intervention

arXiv: https://arxiv.org/abs/2503.05622 · HTML: https://mlsanity.com/paper/2503.05622/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 52 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Builds on (most cited first, 16 of 16)

- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Smart "Predict, then Optimize"](https://mlsanity.com/paper/1710.08005/) (2017)
- [Black Box Variational Inference](https://mlsanity.com/paper/1401.0118/) (2013)
- [Monte Carlo Gradient Estimation in Machine Learning](https://mlsanity.com/paper/1906.10652/) (2019)
- [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)
- [Learning with Differentiable Perturbed Optimizers](https://mlsanity.com/paper/2002.08676/) (2020)
- [Differentiable Patch Selection for Image Recognition](https://mlsanity.com/paper/2104.03059/) (2021)
- [Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective](https://mlsanity.com/paper/2302.01425/) (2023)
- [Variational Bayesian Decision-making for Continuous Utilities](https://mlsanity.com/paper/1902.00792/) (2019)
- [Decision-Focused Learning with Directional Gradients](https://mlsanity.com/paper/2402.03256/) (2024)
- [Decision-Aware Learning for Optimizing Health Supply Chains](https://mlsanity.com/paper/2211.08507/) (2022)
- [Direct loss minimization algorithms for sparse Gaussian processes](https://mlsanity.com/paper/2004.03083/) (2020)
- [CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator](https://mlsanity.com/paper/2110.14002/) (2021)
- [CASTNet: Community-Attentive Spatio-Temporal Networks for Opioid Overdose Forecasting](https://mlsanity.com/paper/1905.04714/) (2019)
- [Machine Learning for Drug Overdose Surveillance](https://mlsanity.com/paper/1710.02458/) (2017)

## Built on by (most cited first, 1 of 1)

- [PruneShift: A Framework for Evaluating Decision Reliability in Structured Pruning](https://mlsanity.com/paper/2608.29765/) (2026)

## Abstract (arXiv)

Optimal allocation of scarce resources is a common problem for decision makers faced with choosing a limited number of locations for intervention. Spatiotemporal prediction models could make such decisions data-driven. A recent performance metric called fraction of best possible reach (BPR) measures the impact of using a model's recommended size K subset of sites compared to the best possible top-K in hindsight. We tackle two open problems related to BPR. First, we explore how to rank all sites numerically given a probabilistic model that predicts event counts jointly across sites. Ranking via the per-site mean is suboptimal for BPR. Instead, we offer a better ranking for BPR backed by decision theory. Second, we explore how to train a probabilistic model's parameters to maximize BPR. Discrete selection of K sites implies all-zero parameter gradients which prevent standard gradient training. We overcome this barrier via advances in perturbed optimizers. We further suggest a training objective that combines likelihood with a decision-aware BPR constraint to deliver high-quality top-K rankings as well as good forecasts for all sites. We demonstrate our approach on two where-to-intervene applications: mitigating opioid-related fatal overdoses for public health and monitoring endangered wildlife.