Advanced Machine Learning with Bilevel Optimization

具有双层优化的高级机器学习

• 批准号: DP230101540
• 负责人: A/Prof Guangquan Zhang
• 金额: $ 33.82万
• 依托单位: University of Technology Sydney
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2023
• 资助国家: 澳大利亚
• 起止时间: 2023-06-01 至 2026-05-31
• 项目状态: 未结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP230101540
• 关键词: Advanced; Machine; Learning; Bilevel; Optimization

There is an urgent need to develop a new machine learning (ML) paradigm that can overcome data-privacy and model-size constraints in real-world applications. This project aims to develop an advanced paradigm of ML with bilevel optimisation, called bilevel ML. A theoretically-guaranteed fast approximate solver and a new fuzzy bilevel learning framework will be developed to achieve the aim in complex situations; a methodology to transfer knowledge and an approach to fast-adapt bilevel optimization solutions when required computing resources change. The anticipated outcomes should significantly improve the reliability of ML with benefits for safety learning and computing resource optimisation in ML-based data analytics.

迫切需要开发一种新的机器学习（ML）范式，以克服现实应用中的数据隐私和模型大小限制。该项目旨在开发一种具有双层优化的高级 ML 范式，称为双层 ML。将开发理论上保证的快速近似求解器和新的模糊双层学习框架以在复杂情况下实现目标；当所需的计算资源发生变化时，一种转移知识的方法和一种快速适应双层优化解决方案的方法。预期结果应显着提高机器学习的可靠性，并有利于基于机器学习的数据分析中的安全学习和计算资源优化。