# Stochastic Weight Averaging in Parallel: Large-Batch Training that Generalizes Well

Source: [Stochastic Weight Averaging in Parallel: Large-Batch Training that Generalizes Well](<https://www.sota2.com/research/paper/68fa66e21e209131cea12d2c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:00:46.769Z

Authors: Vipul Gupta, Santiago Akle Serrano, Dennis DeCoste

Published: 2020-01-07T23:13:35.000Z

## Abstract

We propose Stochastic Weight Averaging in Parallel (SWAP), an algorithm to accelerate DNN training. Our algorithm uses large mini-batches to compute an approximate solution quickly and then refines it by averaging the weights of multiple models computed independently and in parallel. The resulting models generalize equally well as those trained with small mini-batches but are produced in a substantially shorter time. We demonstrate the reduction in training time and the good generalization performance of the resulting models on the computer vision datasets CIFAR10, CIFAR100, and ImageNet.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2001.02312>)

[PDF](<https://arxiv.org/pdf/2001.02312.pdf>)