Decision-Aware Training for Sample-Based Generative Models
For practitioners using probabilistic forecasts in high-stakes decisions, this method reduces costly forecast errors without sacrificing overall forecast quality.
Proposed decision-aware training for sample-based generative models by augmenting the energy score with a differentiable decision loss, improving cost-sensitive forecast accuracy while retaining full probabilistic forecasts, validated on synthetic and two real-world tasks.
Sample-based generative models are increasingly used for probabilistic forecasting in high-stakes decision settings, yet their training objectives are blind to the decision maker's cost structure. These models are commonly trained with strictly proper scoring rules, such as the energy score, which allocate their training signal in proportion to data density, with no awareness of where forecast errors are most costly for downstream decisions. We therefore propose decision-aware training for sample-based generative models, augmenting the energy score objective with a differentiable decision loss that directly penalises the cost incurred by acting on the model's forecast. This combined loss is theoretically grounded, as the decision loss is itself a proper scoring rule. We validate our method on one synthetic and two real-world tasks, showing targeted improvements in cost-sensitive regions while retaining full probabilistic forecasts.