# Minibatch and Local SGD: Algorithmic Stability and Linear Speedup in Generalization

arXiv: https://arxiv.org/abs/2310.01139 · HTML: https://mlsanity.com/paper/2310.01139/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 53 references that are in the map.
- First posted on arXiv 2 Oct 2023.

## Builds on (most cited first, 30 of 38)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Local SGD Converges Fast and Communicates Little](https://mlsanity.com/paper/1805.09767/) (2018)
- [Train faster, generalize better: Stability of stochastic gradient descent](https://mlsanity.com/paper/1509.01240/) (2015)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning](https://mlsanity.com/paper/1807.06629/) (2018)
- [Tighter Theory for Local SGD on Identical and Heterogeneous Data](https://mlsanity.com/paper/1909.04746/) (2019)
- [Don't Use Large Mini-Batches, Use Local SGD](https://mlsanity.com/paper/1808.07217/) (2018)
- [Private Stochastic Convex Optimization with Optimal Rates](https://mlsanity.com/paper/1908.09970/) (2019)
- [Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses](https://mlsanity.com/paper/2006.06914/) (2020)
- [Is Local SGD Better than Minibatch SGD?](https://mlsanity.com/paper/2002.07839/) (2020)
- [Minibatch vs Local SGD for Heterogeneous Distributed Learning](https://mlsanity.com/paper/2006.04735/) (2020)
- [Mini-batch Stochastic Approximation Methods for Nonconvex Stochastic Composite Optimization](https://mlsanity.com/paper/1308.6594/) (2013)
- [Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent](https://mlsanity.com/paper/2006.08157/) (2020)
- [Stability and Generalization of Learning Algorithms that Converge to Global Optima](https://mlsanity.com/paper/1710.08402/) (2017)
- [High probability generalization bounds for uniformly stable algorithms with nearly optimal rate](https://mlsanity.com/paper/1902.10710/) (2019)
- [Sharper bounds for uniformly stable algorithms](https://mlsanity.com/paper/1910.07833/) (2019)
- [Data-Dependent Stability of Stochastic Gradient Descent](https://mlsanity.com/paper/1703.01678/) (2017)
- [Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints](https://mlsanity.com/paper/1707.05947/) (2017)
- [SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation](https://mlsanity.com/paper/2006.10311/) (2020)
- [Optimal Rates for Spectral Algorithms with Least-Squares Regression over Hilbert Spaces](https://mlsanity.com/paper/1801.06720/) (2018)
- [Stability and Convergence Trade-off of Iterative Optimization Algorithms](https://mlsanity.com/paper/1804.01619/) (2018)
- [Distributed learning with regularized least squares](https://mlsanity.com/paper/1608.03339/) (2016)
- [Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond](https://mlsanity.com/paper/2110.10342/) (2021)
- [Learning with SGD and Random Features](https://mlsanity.com/paper/1807.06343/) (2018)
- [Stability of SGD: Tightness Analysis and Improved Bounds](https://mlsanity.com/paper/2102.05274/) (2021)
- [Stability vs Implicit Bias of Gradient Methods on Separable Data and Beyond](https://mlsanity.com/paper/2202.13441/) (2022)
- [Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters](https://mlsanity.com/paper/2306.03824/) (2023)
- [Differentially Private SGD with Non-Smooth Losses](https://mlsanity.com/paper/2101.08925/) (2021)

## Built on by (most cited first, 5 of 5)

- [Bootstrap SGD: Algorithmic Stability and Robustness](https://mlsanity.com/paper/2409.01074/) (2024)
- [Stability and Generalization for Distributed SGDA](https://mlsanity.com/paper/2411.09365/) (2024)
- [How Does the Smoothness Approximation Method Facilitate Generalization for Federated Adversarial Learning?](https://mlsanity.com/paper/2412.08282/) (2024)
- [Stability-based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning](https://mlsanity.com/paper/2503.01530/) (2025)
- [Generalization and Optimization of SGD with Lookahead](https://mlsanity.com/paper/2509.15776/) (2025)

## Abstract (arXiv)

The increasing scale of data propels the popularity of leveraging parallelism to speed up the optimization. Minibatch stochastic gradient descent (minibatch SGD) and local SGD are two popular methods for parallel optimization. The existing theoretical studies show a linear speedup of these methods with respect to the number of machines, which, however, is measured by optimization errors in a multi-pass setting. As a comparison, the stability and generalization of these methods are much less studied. In this paper, we study the stability and generalization analysis of minibatch and local SGD to understand their learnability by introducing an expectation-variance decomposition. We incorporate training errors into the stability analysis, which shows how small training errors help generalization for overparameterized models. We show minibatch and local SGD achieve a linear speedup to attain the optimal risk bounds.