Current Research Focus

This page is under construction. Our recent publications / preprints provide an idea of the current research in the group.

At a high level, the group's research focus includes high-dimensional statistics and mathematics of machine / deep learning. A few works that exemplify the current interests in the group are:

• Perspective paper on the theory of representation learning [link] with our interests covering optimisation and generalisation [link], and development of kernel methods [link]
• The interplay of optimisation and statistical generalisation both in the context of high-dimensional statistics [link] and deep learning [link]
• Characterisation of the statistical performance of graph neural networks [link] as well as works on robustness certification of graph neural networks [link]