2 papers
math.ST2026
The Zero Pattern of a Design Matrix Drives Multiple Descent in Over-parameterized Regression
Kevin Han Huang, Haoyu Ye, Somak Laha +1
Over-parameterized linear regression has been widely studied over the last decade. However, most existing works assume that the covariates are independent and that their covariance…
stat.ML2026
Graph Attention Network for Node Regression on Random Geometric Graphs with ErdÅs--Rényi contamination
Somak Laha, Suqi Liu, Morgane Austern
Graph attention networks (GATs) are widely used and often appear robust to noise in node covariates and edges, yet rigorous statistical guarantees demonstrating a provable advantag…