3 papers
cs.LG2026
Distributionally Robust Linear Regression With Block Lewis Weights
Naren Sarayu Manoj, Kumar Kshitij Patel
We present an algorithm for the group distributionally robust (GDR) least squares problem. Given groups, a parameter vector in , and stacked design matrices and r…
math.OC2025
A Geometric Approach to Problems in Optimization and Data Science
Naren Sarayu Manoj
We give new results for problems in computational and statistical machine learning using tools from high-dimensional geometry and probability. We break up our treatment into two pa…
stat.ML2024
On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models
Aditya Bhaskara, Agastya Vibhuti Jha, Michael Kapralov +3
In a graph bisection problem, we are given a graph with two equally-sized unlabeled communities, and the goal is to recover the vertices in these communities. A popular heurist…