- New paper: On the Statistical Query Complexity of Learning Semiautomata: a Random Walk Approach
- Our paper 'Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks' was accepted at NeurIPS 2025.
- Aseem Baranwal has won the SCS PhD Dissertation Award!
- Our paper 'Exact Learning of Permutations for Nonzero Binary Inputs with Logarithmic Training Size and Quadratic Ensemble Complexity' was accepted at the 3rd Workshop on High-Dimensional Learning Dynamics (HiLD) at ICML 2025.
- Artur Back de Luca has been awarded the Ontario Graduate Scholarship (OGS) and the President's Graduate Scholarship (PGS).
- Our paper 'Positional Attention: Expressivity and Learnability of Algorithmic Computation' was accepted at ICML 2025.
- Shenghao Yang successfully defended his thesis titled 'Perspectives of Graph Diffusion: Computation, Local Partitioning, Statistical Recovery, and Applications'.
Research Experience
Research focuses on the application of computational learning theory to algorithmic tasks, theoretical understanding of graph neural networks for reasoning and classification applications, and scalable algorithms for detecting communities and clusters in large-scale networks.