most citedOn Regularization via Early Stopping for Least Squares Regression

1 citations · 1 across the 2 of their papers we have counts for

collaborators

14 papers

math.NA2026

On Trimming Tensor-structured Measurements and Efficient Low-rank Tensor Recovery

Shambhavi Suryanarayanan, Elizaveta Rebrova

In this paper, we take a step towards developing efficient hard thresholding methods for low-rank tensor recovery from memory-efficient linear measurements with tensorial structure…

cs.LG20261 cited

On Regularization via Early Stopping for Least Squares Regression

Rishi Sonthalia, Jackie Lok, Elizaveta Rebrova

A fundamental problem in machine learning is understanding the effect of early stopping on the parameters obtained and the generalization capabilities of the model. Even for linear…

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-sta…

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.OC2026

Learning nonnegative matrix factorizations from compressed data

Abraar Chaudhry, Elizaveta Rebrova

We propose a flexible and theoretically supported framework for scalable nonnegative matrix factorization. The goal is to find nonnegative low-rank components directly from compres…

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…