提出新型风险度量，可精准控制数据子群体差异并提供分组保障。
PAC-Bayesian Bounds on Constrained f-Entropic Risk Measures
- 基于f-散度构建约束型熵风险度量，支持对子群体不平衡的精细调控。
- 首次给出该风险度量的分解式PAC-Bayesian界，实现分组层面的泛化保障。
- 设计自界算法直接优化边界，适合关注公平性与鲁棒性的模型开发。
当以期望损失表示风险时，传统的泛化界往往无法捕捉数据中子群体间的失衡问题。为克服此局限，本文引入一类新的风险度量——约束型f-熵风险度量，通过f-散度实现对分布偏移和子群体不平衡的更精细控制，包含条件风险价值（CVaR）这一经典风险度量。我们推导了该类风险的经典与分解式PAC-Bayesian泛化界，首次提供了超越标准风险的分解式PAC-Bayesian保证。基于该理论，我们设计了一种自界算法，可直接最小化这些边界，从而获得具有子群体层面保障的模型。最后，我们在实验中验证了该方法的有效性。
原文摘要 · Abstract (English)
PAC generalization bounds on the risk, when expressed in terms of the expected loss, are often insufficient to capture imbalances between subgroups in the data. To overcome this limitation, we introduce a new family of risk measures, called constrained f-entropic risk measures, which enable finer control over distributional shifts and subgroup imbalances via f-divergences, and include the Conditional Value at Risk (CVaR), a well-known risk measure. We derive both classical and disintegrated PAC-Bayesian generalization bounds for this family of risks, providing the first disintegratedPAC-Bayesian guarantees beyond standard risks. Building on this theory, we design a self-bounding algorithm that minimizes our bounds directly, yielding models with guarantees at the subgroup level. Finally, we empirically demonstrate the usefulness of our approach.
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。