# Don't decay the learning rate, increase the batch size

**Type:** Papers  
**Canonical URL:** https://scholariq.org/papers/don-t-decay-the-learning-rate-increase-the-batch-size-2/

## Facts

| Field | Value |
| --- | --- |
| Author Names | Samuel Smith,Pieter-Jan Kindermans,Chris Ying,Quoc V. Le |
| Citations | 271 |
| Fields | Computer Science |
| Open Access | true |
| OA Status | green |
| OA URL | https://arxiv.org/pdf/1711.00489.pdf |
| OpenAlex ID | https://openalex.org/W2963702144 |
| Type | preprint |
| Year | 2018 |

## Paper authors

- [Samuel Smith](https://scholariq.org/researchers/samuel-smith/)

## Paper journal

- [arXiv (Cornell University)](https://scholariq.org/journals/arxiv-cornell-university/)

## Paper primary topic

- [Advanced Neural Network Applications](https://scholariq.org/topics/advanced-neural-network-applications/)

## Paper topics

- [Advanced Neural Network Applications](https://scholariq.org/topics/advanced-neural-network-applications/)
- [Domain Adaptation and Few-Shot Learning](https://scholariq.org/topics/domain-adaptation-and-few-shot-learning/)
- [Stochastic Gradient Optimization Techniques](https://scholariq.org/topics/stochastic-gradient-optimization-techniques/)

---
Source: ScholarIQ — public research metadata, principally OpenAlex. See https://scholariq.org/sources/ for provenance and https://scholariq.org/methodology/ for what these figures mean.