研究人员开发了一种使用PAC-Bayesian界限来认证二次闭环控制系统的新方法。该方法通过采用系统级综合参数化来解决无界和非Lipschitz损失函数带来的挑战。该方法为控制响应上的后验分布提供了PAC-Bayes-Chernoff证书，并包含一个数据驱动的界限，该界限可以最小化以创建用于控制选择的学习算法。 AI
影响 这项研究可能导致更强大、可认证的AI驱动的控制系统，尤其是在数据有限的情况下。
排序理由 该集群包含一篇详细介绍控制系统新颖方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.28281v1 Announce Type: cross Abstract: PAC-Bayesian bounds provide finite-sample guarantees for data-dependent randomized predictors, but applying them to learning-based control is difficult because the natural objective is a quadratic trajectory cost. Such losses are …
PAC-Bayesian bounds provide finite-sample guarantees for data-dependent randomized predictors, but applying them to learning-based control is difficult because the natural objective is a quadratic trajectory cost. Such losses are unbounded, non-Lipschitz , and lead to response-de…