New VR project: Investigating deep learning through the lens of adaptive kernels
There is no denying that deep neural networks have had a profound impact on research across statistics, data science and machine learning, as well as significantly altered the analytical landscape in many application areas, including bioinformatics and systems biology. While previous research efforts were focused on the then surprisingly excellent performance of deep neural networks, the field is now shifting toward trying to explain this performance through connections to classical statistical methodologies, specifically through kernel learning, where models are generated via first principles by borrowing predictive strength across similar sets of observations.
In this project, we explore the connection between deep and kernel learning in multiple directions. First, we recast the kernel learning through regression approximations of gradient descent. This provides a transparent framework through which we can gain a better understanding on how we can extend classical statistical methods to be more flexible, and thus mimic the properties of deep learners. Secondly, we propose to train deep and kernel learners in a coupled fashion, to enable the classical methods to reach the performance levels of the deep learners. Thirdly, we propose to explore how these methods can be used for flexible, yet interpretable and robust modeling of large-scale biobank and cancer genomic data.
We will recruit one doctoral student in statistics and machine learning to work on this project. Starting date is August 2025. In this project, you will explore the connection between deep and kernel learning in multiple directions; (i) how the models learn, (ii) how the models can be trained jointly to enable the classical methods to reach the performance levels of the deep learners, and (iii) how these methods can be used for flexible, yet interpretable and robust modeling of large-scale biobank and cancer genomic data.
To qualify for the position you must have obtained a master’s degree or a 4-year bachelor’s degree in mathematics, applied mathematics, mathematical statistics, or other relevant field or expect to complete such a degree prior to the start of the employment. Good presentation and communication skills in oral and written English are required. Experience/expertise in one or several of the following areas may be meritorious: theory of deep neural networks, high-dimensional statistics, kernel methods, and advanced programming. Only applications through the electronic system will be considered.