Nonmonotone Algorithms in Operator Splitting, Optimisation and Data Science

算子分裂、优化和数据科学中的非单调算法

• 批准号: DE200100063
• 负责人: Dr Matthew Tam
• 金额: $ 29.63万
• 依托单位: The University of Melbourne
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Early Career Researcher Award
• 财政年份: 2020
• 资助国家: 澳大利亚
• 起止时间: 2020-06-04 至 2023-09-09
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DE200100063
• 关键词: Nonmonotone; Algorithms; Operator; Splitting; Optimisation

This project aims to develop the mathematical foundations for the analysis and development of optimisation algorithms used in data science. Despite their now ubiquitous use, machine learning software packages routinely rely on a number of algorithms from mathematical optimisation which are not properly understood. By moving beyond the traditional realms of Fejér monotone algorithms, this project expects to develop the mathematical theory required to rigorously justify the use of such algorithms and thereby ensure the integrity of the decision tools they produce. This mathematical framework is also expected to produce new algorithms for optimisation which benefit consumers of data science such as the health-care and cybersecurity sectors.

该项目旨在为数据科学中使用的优化算法的分析和开发奠定数学基础。尽管机器学习软件包现在无处不在，但它们通常依赖于数学优化中的许多算法，这些算法尚未得到正确理解。通过超越Fejér单调算法的传统领域，该项目希望开发所需的数学理论，以严格证明此类算法的使用，从而确保其产生的决策工具的完整性。这种数学框架还有望产生新的优化算法，使医疗保健和网络安全部门等数据科学消费者受益。