模型预测未必最优，需针对决策目标定制。
All AI Models are Wrong, but Some are Optimal
- 提出判断预测模型是否能支持最优决策的严格条件
- 证明仅拟合数据的模型常导致次优决策
- 指导构建面向决策优化的预测模型
预测未来行为的AI模型在智能决策中至关重要，但通常基于数据拟合，倾向于预测最可能结果而非支持最优决策。这种假设在理论和实践中均不成立。本文建立了预测模型实现最优决策政策的必要且充分条件，并探讨其对序列决策中构建预测模型的启示。研究显示，预测模型必须根据具体决策目标进行设计，否则即使预测准确也可能导致决策失效。
原文摘要 · Abstract (English)
AI models that predict the future behavior of a system (a.k.a. predictive AI models) are central to intelligent decision-making. However, decision-making using predictive AI models often results in suboptimal performance. This is primarily because AI models are typically constructed to best fit the data, and hence to predict the most likely future rather than to enable high-performance decision-making. The hope that such prediction enables high-performance decisions is neither guaranteed in theory nor established in practice. In fact, there is increasing empirical evidence that predictive models must be tailored to decision-making objectives for performance. In this paper, we establish formal (necessary and sufficient) conditions that a predictive model (AI-based or not) must satisfy for a decision-making policy established using that model to be optimal. We then discuss their implications for building predictive AI models for sequential decision-making.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。