研究人员开发了一种新方法，用于在差分隐私约束下处理异质协变量尺度时稳定LASSO算法。他们的方法，称为基于Gram的各向异性目标扰动，旨在抵消由变化的协变量结构引起的失真，而无需消耗额外的隐私预算。该技术使用近似消息传递框架进行分析，据报道，与传统的均匀噪声注入相比，它增强了收敛稳定性，并提高了统计效率和隐私性能。 AI
影响 引入了一种在不牺牲效率的情况下增强统计估计隐私的新技术。
排序理由 关于隐私保护机器学习新颖统计方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.01492v1 Announce Type: new Abstract: We study high-dimensional LASSO under differential privacy via objective perturbation with heterogeneous covariate scales. In practical scenarios, covariates often exhibit diverse scales; however, standard preprocessing is problemat…
We study high-dimensional LASSO under differential privacy via objective perturbation with heterogeneous covariate scales. In practical scenarios, covariates often exhibit diverse scales; however, standard preprocessing is problematic under privacy constraints, as it consumes add…