A key component of machine learning is mathematical optimization, that is used, for example, to train neural networks. The goal of this project is to provide new analysis and tools for optimization problems and algorithms arising in machine learning, but also to use insights and tools from machine learning to improve optimization methods. This explains the project title ‘Optimization for and with machine learning’.
The project consists of four connected work packages. The first two work packages are related to ‘optimization for machine learning’.
The Postdoc will work on topics related to work package 2.
The main objectives will be to investigate and exploit structural properties of data, which can be geometric, algebraic or combinatorial, for the design of dedicated solution approaches. Special areas of focus include (but are not limited to): investigate the use of polynomial functions in machine learning, which links to polynomial optimization, an area that has been extensively studied in the optimization field in recent years; investigate combinatorial algorithms for detecting structural properties of data points, given through their pairwise similarities.
Candidates are required to have a completed PhD in the area of Mathematics or Operations Research with a strong mathematical background. A strong affinity with algebraic, combinatorial and geometric methods and with expertise in optimization (semidefinite programming) is required; some background in machine learning is preferred. Needed qualifications for candidates include proven research talent and good academic writing and presentation skills. Candidates are expected to have an excellent command of English.