CAREER: Differentially-Private Machine Learning with Applications to Biomedical Informatics

对大规模患者病历进行机器学习可以发现新的全人群模式，使其能够在遗传学、疾病机制、药物发现、医疗保健政策和公共卫生方面取得进展。然而，对患者隐私的担忧阻碍了生物医学研究人员在大量患者数据上运行他们的算法，这为通过机器学习进行重要的新发现制造了障碍。该项目的目标是通过开发隐私保护工具来查询、聚集、分类和分析医学数据库来解决这一障碍。特别是，该项目旨在确保差异隐私-由密码学家设计的正式的隐私数学概念，近年来在系统、算法、机器学习和数据采掘界获得了相当大的关注。将差异私有机器学习工具应用于生物医学信息学的主要挑战是缺乏统计效率或所需的大量样本。该项目将通过利用PI的专业知识开发差异私有和统计高效的机器学习工具来克服这一挑战，用于分类和聚类。这项拟议的研究将结合差异隐私、统计学、机器学习和数据库算法的见解，推动隐私保护数据分析的最先进水平。这项拟议的研究与加州大学圣迭戈分校本科生和研究生课程的发展密切相关，纳入了PI的新本科机器学习课程、新的研究生学习理论课程，并更新了算法设计和分析课程。相应的材料将通过国际刑警组织的网站公开传播。该协会坚定地致力于增加妇女和少数群体的参与，并将开展外联活动，以吸引和留住计算机科学领域的妇女。

Machine learning on large-scale patient medical records can lead to the discovery of novel population-wide patterns enabling advances in genetics, disease mechanisms, drug discovery, healthcare policy, and public health. However, concerns over patient privacy prevent biomedical researchers from running their algorithms on large volumes of patient data, creating a barrier to important new discoveries through machine-learning. The goal of this project is to address this barrier by developing privacy-preserving tools to query, cluster, classify and analyze medical databases. In particular, the project aims to ensure differential privacy --- a formal mathematical notion of privacy designed by cryptographers which has gained considerable attention in the systems, algorithms, machine-learning and data-mining communities in recent years. The primary challenge in applying differentially-private machine learning tools to biomedical informatics is the lack of statistical efficiency, or the large number of samples required.The project will overcome this challenge by drawing on insights obtained from the PI's expertise to develop differentially-private and highly statistically-efficient machine learning tools for classification and clustering. The proposed research will advance the state-of-the-art in privacy-preserving data analysis by combining insights from differential privacy, statistics, machine learning, and database algorithms. The proposed research is closely tied to the development of the undergraduate and graduate curricula at UCSD, feeding into the PI's new undergraduate machine learning class, a new graduate learning theory class, and updates to an algorithm design and analysis class. The corresponding materials will be publicly disseminated through the PI's website. The PI is strongly committed to increasing the participation of women and minorities, and will engage in outreach activities to attract and retain women in computer science.