论文标题
具有可行性保证的差异私人凸优化
Differentially Private Convex Optimization with Feasibility Guarantees
论文作者
论文摘要
本文开发了一个新型的差异私人框架，以通过敏感优化数据和复杂的物理或操作约束来解决凸优化问题。与主要对问题数据（目标或解决方案）作用的标准噪声添加算法不同，并忽略了问题的限制，此框架要求优化变量是噪声的函数，并利用了与正式可行性保证的偶然限制的问题重新印象。对噪声进行校准，以在优化解决方案上为身份和线性查询提供差异隐私。对于许多应用程序，包括资源分配问题，所提出的框架在预期的最佳损失与优化结果的差异之间提供了权衡。
This paper develops a novel differentially private framework to solve convex optimization problems with sensitive optimization data and complex physical or operational constraints. Unlike standard noise-additive algorithms, that act primarily on the problem data, objective or solution, and disregard the problem constraints, this framework requires the optimization variables to be a function of the noise and exploits a chance-constrained problem reformulation with formal feasibility guarantees. The noise is calibrated to provide differential privacy for identity and linear queries on the optimization solution. For many applications, including resource allocation problems, the proposed framework provides a trade-off between the expected optimality loss and the variance of optimization results.
