Decision-Aware Training for Sample-Based Generative Models
cs.LG, stat.ML
Submitted: 2026-07-01
Updated: 2026-10-02
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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.
Terminology
Abstract
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.
Sources
- FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale
- ArchesWeather & ArchesWeatherGen: a deterministic and generative model for efficient ML weather forecasting
- Distributional Diffusion Models with Scoring Rules
- Three Types of Calibration with Properties and their Semantic and Formal Relationships
- Smooth Calibration and Decision Making
- Adam: A Method for Stochastic Optimization
- Improved probabilistic regression using diffusion models
- AIFS-CRPS: Ensemble forecasting using a model trained with a loss function based on the Continuous Ranked Probability Score
- Learning in Implicit Generative Models
- GenCast: Diffusion-based ensemble forecasting for medium-range weather
- Score-Based Generative Modeling through Stochastic Differential Equations
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks