3 papers
cs.LG2025
Learning from Heterophilic Graphs: A Spectral Theory Perspective on the Impact of Self-Loops and Parallel Edges
Kushal Bose, Swagatam Das
Graph heterophily poses a formidable challenge to the performance of Message-passing Graph Neural Networks (MP-GNNs). The familiar low-pass filters like Graph Convolutional Network…
cs.LG2025
Transformers Are Universally Consistent
Sagar Ghosh, Kushal Bose, Swagatam Das
Despite their central role in the success of foundational models and large-scale language modeling, the theoretical foundations governing the operation of Transformers remain only…
stat.ML2024
On the Universal Statistical Consistency of Expansive Hyperbolic Deep Convolutional Neural Networks
Sagar Ghosh, Kushal Bose, Swagatam Das
The emergence of Deep Convolutional Neural Networks (DCNNs) has been a pervasive tool for accomplishing widespread applications in computer vision. Despite its potential capability…