4 papers
The Value of Depth in Message Passing on Sparse Graphs: A Kesten-Stigum Dichotomy
Aseem Raj Baranwal
How deep does a graph neural network need to be on a sparse graph? We study its purest statistical form: node classification on the sparse contextual stochastic block model (CSBM)…
Analysis of Corrected Graph Convolutions
Robert Wang, Aseem Baranwal, Kimon Fountoulakis
Machine learning for node classification on graphs is a prominent area driven by applications such as recommendation systems. State-of-the-art models often use multiple graph convo…
Repetitions in infinite palindrome-rich words
Aseem Raj Baranwal, Jeffrey Shallit
Rich words are characterized by containing the maximum possible number of distinct palindromes. Several characteristic properties of rich words have been studied; yet the analysis…
Critical exponent of infinite balanced words via the Pell number system
Aseem Raj Baranwal, Jeffrey Shallit
In a recent paper of Rampersad et al., the authors conjectured that the smallest possible critical exponent of an infinite balanced word over a 5-letter alphabet is . We prove…