activity
20182026
most citedRandomized Kaczmarz Methods with Beyond-Krylov Convergence

1 citations · 1 across the 11 of their papers we have counts for

collaborators
Showing 2026Show all

5 papers · 1 filter

cs.LG2026

Quantile-based Loss Filtering for Outlier-Robust Stochastic Gradient Descent

Jamie Haddock, Anna Ma, Elizaveta Rebrova

We study loss-based filtering for finite-sum optimization with a subset of corrupted component functions whose gradients may be highly unreliable. Motivated by minimum-loss-based S…

stat.ML2026

Inference for Newton Methods with Accelerated Sketch-and-Project via Random Scaling

Xinchen Du, Elizaveta Rebrova, Michał Dereziński +1

We study an online sketched Newton method that approximates the Newton direction at each step via a state-of-the-art sketching solver, called the generalized accelerated sketch-and…

math.NA2026

Towards Universal Convergence of Backward Error in Linear System Solvers

Michał Dereziński, Yuji Nakatsukasa, Elizaveta Rebrova

The quest for an algorithm that solves an linear system in time complexity, or when solving up to relative error, is a long-stand…

math.NA2026

Attention Mechanisms Through the Lens of Numerical Methods: Approximation Methods and Alternative Formulations

Michel Fabrice Serret, Alice Cortinovis, Yijun Dong +10

The attention mechanism is the computational core of modern Transformer architectures, but its quadratic complexity in the input sequence length is the bottleneck for large-scale i…

math.NA2026

Quantile Randomized Kaczmarz Algorithm with Whitelist Trust Mechanism

Sofiia Shvaiko, Longxiu Huang, Elizaveta Rebrova

Randomized Kaczmarz (RK) is a simple and fast solver for consistent overdetermined systems, but it is known to be fragile under noise. We study overdetermined linear sy…