Open positions
I'm looking for one full-time PhD student (home or international) in learning theory (statistical learning theory and deep learning theory) or theoretical-oriented topics, e.g., trustworthy machine learning, efficient machine learning. This position is full-funded and research-oriented. Besides, applications from other sources of scholarship are also welcome, e.g., Chancellor's International Scholarship for EU/International applicants as well as CSC for Chinese applicants.
My research to theoretically understand why ML models perform well or design efficient (and/or) robust algorithms. Possible topics include (but are not limited to)
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.
Besides, I also work on kernel methods, random features, and some theoretical-oriented application topics, e.g., distribution shift. If you’re interested in, feel free to reach out.
Candidate's profile: The successful candidate is expected to have a solid background in applied mathematics, statistics, computer science or related discipline. Besides, applicants must also meet the University of Warwick minimum entry requirements for the MPhil/PhD course in Computer Science. Refer to official application process for details, including
A good bachelors degree (UK 2.1 level or above or international equivalent) Proficiency in English (both oral and written). Good communication and technical writing skills. Strong maths background (Linear Algebra and Probability knowledge is a plus).
English Proficiency level of IELTS 6.5 overall, with all components at 6.0. (International applicants need ATAS clearance).
The salary and benefits are comparable to other top universities in the UK, and the cost of living near Warwick is significantly lower.
Application: Please send an email to me with your CV and transcript as well as a brief description of your research interests and why you want to work with me. Due to a large number of requests, I, unfortunately, may not be able to reply to all the emails regarding PhD applications. But if your enquires are inline with my research, I will contact you.
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. It offers a unique environment for research on the mathematical aspects of computer science among the top theory groups in the UK.