# Rethinking Machine Learning Development and Deployment for Edge Devices

arXiv: https://arxiv.org/abs/1806.07846 · HTML: https://mlsanity.com/paper/1806.07846/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2018.

## Built on by (most cited first, 4 of 4)

- [Domain Adaptable Fine-Tune Distillation Framework For Advancing Farm Surveillance](https://mlsanity.com/paper/2402.07059/) (2024)
- [Adaptive Beam Search to Enhance On-device Abstractive Summarization](https://mlsanity.com/paper/2201.02739/) (2021)
- [Quantitative Movement Testing: Measuring Chronic Pain Patient Movements from a Single Smartphone Video](https://mlsanity.com/paper/2606.02301/) (2026)
- [Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs](https://mlsanity.com/paper/2608.26069/) (2026)

## Abstract (arXiv)

Machine learning (ML), especially deep learning is made possible by the availability of big data, enormous compute power and, often overlooked, development tools or frameworks. As the algorithms become mature and efficient, more and more ML inference is moving out of datacenters/cloud and deployed on edge devices. This model deployment process can be challenging as the deployment environment and requirements can be substantially different from those during model development. In this paper, we propose a new ML development and deployment approach that is specially designed and optimized for inference-only deployment on edge devices. We build a prototype and demonstrate that this approach can address all the deployment challenges and result in more efficient and high-quality solutions.