# Inexact SARAH Algorithm for Stochastic Optimization

arXiv: https://arxiv.org/abs/1811.10105 · HTML: https://mlsanity.com/paper/1811.10105/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2018.

## Built on by (most cited first, 12 of 12)

- [Optimal variance-reduced stochastic approximation in Banach spaces](https://mlsanity.com/paper/2201.08518/) (2022)
- [Zeroth-Order Alternating Gradient Descent Ascent Algorithms for a Class of Nonconvex-Nonconcave Minimax Problems](https://mlsanity.com/paper/2211.13668/) (2022)
- [Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad](https://mlsanity.com/paper/2403.02648/) (2024)
- [Random-reshuffled SARAH does not need a full gradient computations](https://mlsanity.com/paper/2111.13322/) (2021)
- [Training Structured Neural Networks Through Manifold Identification and Variance Reduction](https://mlsanity.com/paper/2112.02612/) (2021)
- [Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features](https://mlsanity.com/paper/2304.11737/) (2023)
- [FLECS-CGD: A Federated Learning Second-Order Framework via Compression and Sketching with Compressed Gradient Differences](https://mlsanity.com/paper/2210.09626/) (2022)
- [Variance Reduction Methods Do Not Need to Compute Full Gradients: Improved Efficiency through Shuffling](https://mlsanity.com/paper/2502.14648/) (2025)
- [Zeroth-Order Stochastic Mirror Descent Algorithms for Minimax Excess Risk Optimization](https://mlsanity.com/paper/2408.12209/) (2024)
- [Versatile Single-Loop Method for Gradient Estimator: First and Second Order Optimality, and its Application to Federated Learning](https://mlsanity.com/paper/2209.00361/) (2022)
- [SARAH-based Variance-reduced Algorithm for Stochastic Finite-sum Cocoercive Variational Inequalities](https://mlsanity.com/paper/2210.05994/) (2022)
- [Adjusted Shuffling SARAH: Advancing Complexity Analysis via Dynamic Gradient Weighting](https://mlsanity.com/paper/2506.12444/) (2025)

## Abstract (arXiv)

We develop and analyze a variant of the SARAH algorithm, which does not require computation of the exact gradient. Thus this new method can be applied to general expectation minimization problems rather than only finite sum problems. While the original SARAH algorithm, as well as its predecessor, SVRG, require an exact gradient computation on each outer iteration, the inexact variant of SARAH (iSARAH), which we develop here, requires only stochastic gradient computed on a mini-batch of sufficient size. The proposed method combines variance reduction via sample size selection and iterative stochastic gradient updates. We analyze the convergence rate of the algorithms for strongly convex and non-strongly convex cases, under smooth assumption with appropriate mini-batch size selected for each case. We show that with an additional, reasonable, assumption iSARAH achieves the best known complexity among stochastic methods in the case of non-strongly convex stochastic functions.