4-Year PhD Studentship in Data-efficient Machine Learning Methods (NTU, Singapore) Nanyang Technological University (NTU) in Singapore

Training machine learning algorithms on large volumes of data is expensive. In this project, we will develop new algorithms that reduce this computational cost by accounting for the information content of each observation, as well as the difficulty of prediction for different areas of the observation space.

The methods will be numerically evaluated on various machine learning test problems. Explainability and uncertainty quantification will be considered as well.

In addition to algorithmic advances, the project will also develop a mathematical theory based on PAC-Bayes generalization bounds.

Students with strong computational and mathematical backgrounds are encouraged to contact me directly at [email protected] . You can find out more about my research at my website https://sites.google.com/site/paulindani/ .

A fully funded NTU Research Scholarship is available for this project,

https://www.ntu.edu.sg/admissions/graduate/financialmatters/scholarships/rss#Content_C006_Col00

For international applicants, this is 2700 SGD for the first year, and 3200 SGD later on after passing the required courses and doing an oral presentation about the research plans.

Applications for an August 2025 start will be considered until the 15th of May, 2025.