PhD Studentship in the Topic of Machine Learning (Learning Theory or Trustworthy Machine Learning)

One PhD studentship is available in the area of machine learning theory (statistical learning theory and deep learning theory) or theoretical-oriented topics, e.g., trustworthy machine learning, efficient machine learning. The project aims to theoretically understand why machine learning models perform well and/or design efficient and robust algorithms in trustworthy machine learning. 

The topics include but not limited to 

1. Statistical-computational gap in modern machine learning
2. Robustness of neural networks for trustworthy ML systems
3. Fine-tuning of modern machine learning models

The successful candidate is expected to have a solid background in applied mathematics/statistics/computer science or related discipline. Advanced coding skills are a big plus. 

This position is fully-funded and research-oriented. Candidates interested in the following topics are invited to contact Dr Liu: 

• Statistical-computational gap in modern machine learning: It delves into a pivotal question within the machine learning community: how can we theoretically explain the empirical phenomena observed in over-parameterized models from the perspective of statistical and computational side? Our target is to bridge the gap between empirical observations and rigorous theoretical assurances, particularly in the context of neural networks.
• Robustness of neural networks for trustworthy ML systems: It aims to build a trustworthy ML system from the theoretical and/or empirical side. Theoretically, we aim to understand the robust-accuracy trade-off. Empirically, efficient training algorithms are designed for the improvement of robustness.
• Fine-tuning of modern machine learning models: It aims to theoretically understand the mystery of fine-tuning or devise expeditious and resource-efficient inference and fine-tuning methods for LLMs, enabling their deployment within constrained computational resources.

Dr Liu also works on kernel methods and some theoretical-oriented application topics, e.g., distribution shift. If you’re interested in, feel free to reach out.

Applicants must also meet the University of Warwick minimum entry requirements for the MPhil/PhD course in Computer Science (warwick.ac.uk). Applicants must have at least a degree equivalent to a UK 2.1, and English Proficiency level of IELTS 6.5 overall, with all components at 6.0. (International applicants need ATAS clearance).

For further details please contact Dr. Fanghui Liu (fanghui.liu@warwick.ac.uk), Assistant Professor at University of Warwick. Information on Dr Liu can be found here (www.lfhsgre.org).

About Warwick: The University of Warwick has one of the leading Computer Science departments in the UK (ranked 4th UK computer science department in the 2021 research excellence framework). The department, particularly well-known for its research in theoretical computer science, consistently produces top quality research and has strong links with research from the Warwick Mathematics Institute. (The Department of Computer Science and the Mathematics Institute are adjacent and physically connected, which offers a unique environment for research on the mathematical aspects of computer science among the top theory groups in the UK.)

Funding Details

Full payment of tuition fees and an annual stipend at the UKRI rate for 3.5 years.

Advert information