精选理由
这篇论文用置信带兜底，保证模型更新不会越改越差，适合需要稳妥迭代的场景。
本文提出局部总体风险证书(Local Population-Risk Certificates)，为当前模型θ周围的候选方向v∈D构建ℓ_{θ+v}-ℓ_θ的两面置信带。该证书的上端点作为风险控制更新规则：仅当上端点非正时才接受更新，否则保留当前模型。这种方法保证了更新不会增加总体风险，为安全模型更新提供了理论保障。
原文 · arXiv cs.LG
On Local Population-Risk Certificates
This paper develops local certificates for population-risk increments around a current model. For a local candidate set \(\mathcal D\), the certificate is a two-sided confidence band for \(P({\ell_{θ+v}-\ell_θ})\) over \(v\in\mathcal D\). As an application, the upper endpoint of this band yields a risk-controlled update rule: an update is accepted only when its certified upper endpoint is nonpositive; otherwise the current model is retained.