My research focuses on the foundations and applications of graph methods in machine learning. I aim to find elegant explanations for phenomena associated with learning and to exploit them in order to design principled solutions. I am also interested in the theoretical analysis of neural networks and in using deep learning techniques to solve bio-engineering problems (especially protein design).
Selected recent works
Y. Dong, J.B. Cordonnier, A. Loukas. Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth. 2021. (preprint, bibtex, blogpost)
N. Karalias, A. Loukas. Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs. Oral at NeurIPS 2020. (paper, bibtex, video starts at 36:54, blogpost, slides)