Decision-Aware Training for Sample-Based Generative Models

• URL: http://arxiv.org/abs/2607.01171v1
• Date: Wed, 01 Jul 2026 17:02:23 GMT
• Title: Decision-Aware Training for Sample-Based Generative Models
• Abstract summary: We 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.<n>We validate our method on one synthetic and two real-world tasks, showing targeted improvements in cost-sensitive regions while retaining full probabilistic forecasts.
• Score: 0.08594140167290099
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias [4.124127724629818]
  We study how a prediction model will perform in a new environment before deployment.<n>We present a double machine learning procedure for estimating the target risk of an arbitrary black-box prediction model.<n>We evaluate our estimator through experiments using the eICU electronic health records database.
  arXiv  Detail & Related papers  (2026-06-12T14:39:03Z)
• Auditing and Fixing Economic Validity in Tabular Foundation Models for Discrete Choice [12.709654635425442]
  Tabular foundation models achieve strong accuracy on choice prediction tasks.<n>But their predictions often violate the economic logic those tasks require.<n>We propose a two-stage adapter that embeds foundation model predictions within a utility-maximization framework.
  arXiv  Detail & Related papers  (2026-05-26T05:13:20Z)
• Act or Escalate? Evaluating Escalation Behavior in Automation with Language Models [0.0]
  We model escalation as a decision under uncertainty.<n>We find marked differences in the implicit thresholds models use to trade off these costs.<n>We then test interventions that target this decision process by varying cost ratios.
  arXiv  Detail & Related papers  (2026-03-31T19:29:17Z)
• Rejection via Learning Density Ratios [50.91522897152437]
  Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions.<n>We propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance.<n>Our framework is tested empirically over clean and noisy datasets.
  arXiv  Detail & Related papers  (2024-05-29T01:32:17Z)
• Robust Losses for Decision-Focused Learning [2.9652474178611405]
  Decision-focused learning aims at training the predictive model to minimize regret by making a suboptimal decision. empirical regret can be an ineffective surrogate because empirical optimal decisions can vary substantially from expected optimal decisions. We propose three novel loss functions that approximate expected regret more robustly.
  arXiv  Detail & Related papers  (2023-10-06T15:45:10Z)
• Learning Sample Difficulty from Pre-trained Models for Reliable Prediction [55.77136037458667]
  We propose to utilize large-scale pre-trained models to guide downstream model training with sample difficulty-aware entropy regularization. We simultaneously improve accuracy and uncertainty calibration across challenging benchmarks.
  arXiv  Detail & Related papers  (2023-04-20T07:29:23Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• Dense Uncertainty Estimation [62.23555922631451]
  In this paper, we investigate neural networks and uncertainty estimation techniques to achieve both accurate deterministic prediction and reliable uncertainty estimation. We work on two types of uncertainty estimations solutions, namely ensemble based methods and generative model based methods, and explain their pros and cons while using them in fully/semi/weakly-supervised framework.
  arXiv  Detail & Related papers  (2021-10-13T01:23:48Z)
• Estimating Generalization under Distribution Shifts via Domain-Invariant Representations [75.74928159249225]
  We use a set of domain-invariant predictors as a proxy for the unknown, true target labels. The error of the resulting risk estimate depends on the target risk of the proxy model.
  arXiv  Detail & Related papers  (2020-07-06T17:21:24Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.