3 papers
cs.LG2026
Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation
Zhankun Luo, Antesh Upadhyay, M. Berk Sahin +3
Stochastic estimators are fundamental to large-scale optimization, where population quantities must be inferred from noisy oracle observations. Although influential methods such as…
cs.LG2026
Beyond Bounded Variance: Variance-Reduced Normalized Methods for Nonconvex Optimization under Blum-Gladyshev Noise
Antesh Upadhyay, Arda Fazla, Abolfazl Hashemi
We study nonconvex stochastic optimization under the Blum-Gladyshev (-0) noise model, where the stochastic gradient variance grows quadratically with the distance from…
cs.LG2026
RAMPAGE: RAndomized Mid-Point for debiAsed Gradient Extrapolation
Zhankun Luo, M. Berk Sahin, Antesh Upadhyay +2
A celebrated method for Variational Inequalities (VIs) is Extragradient (EG), which can be viewed as a standard discrete-time integration scheme. With this view in mind, in this pa…