In today's world, machine learning is hard to imagine without large training datasets and models. This has led to the use of stochastic methods for training, such as stochastic gradient descent (SGD). SGD provides weak theoretical guarantees of convergence, but there are modifications, such as Stochastic Variance Reduced Gradient (SVRG) and StochAstic Recursive grAdient algoritHm (SARAH), that can reduce the variance. These methods require the computation of the full gradient occasionally, which can be time consuming. In this paper, we explore variants of variance reduction algorithms that eliminate the need for full gradient computations. To make our approach memory-efficient and avoid full gradient computations, we use two key techniques: the shuffling heuristic and idea of SAG/SAGA methods. As a result, we improve existing estimates for variance reduction algorithms without the full gradient computations. Additionally, for the non-convex objective function, our estimate matches that of classic shuffling methods, while for the strongly convex one, it is an improvement. We conduct comprehensive theoretical analysis and provide extensive experimental results to validate the efficiency and practicality of our methods for large-scale machine learning problems.
View on arXiv@article{medyakov2025_2502.14648,
title={ Variance Reduction Methods Do Not Need to Compute Full Gradients: Improved Efficiency through Shuffling },
author={ Daniil Medyakov and Gleb Molodtsov and Savelii Chezhegov and Alexey Rebrikov and Aleksandr Beznosikov },
journal={arXiv preprint arXiv:2502.14648},
year={ 2025 }
}