2 papers
math.NA2026
Debiasing Random Oblique Projections for Subsampled OLS and Fast CUR in High Dimensions
Chengmei Niu, Sachin Garg, MichaÅ DereziÅski +1
Random sampling is a fundamental tool in modern machine learning and numerical linear algebra for reducing the computational cost of large-scale matrix problems. Existing analyses,…
math.OC2025
Stochastic Variance-Reduced Newton: Accelerating Finite-Sum Minimization with Large Batches
MichaÅ DereziÅski
Stochastic variance reduction has proven effective at accelerating first-order algorithms for solving convex finite-sum optimization tasks such as empirical risk minimization. Inco…