# On-Device Machine Learning: An Algorithms and Learning Theory Perspective

arXiv: https://arxiv.org/abs/1911.00623 · HTML: https://mlsanity.com/paper/1911.00623/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2019.

## Built on by (most cited first, 30 of 63)

- [EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization](https://mlsanity.com/paper/2303.01904/) (2023)
- [Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances](https://mlsanity.com/paper/2111.00418/) (2021)
- [Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models](https://mlsanity.com/paper/2503.06027/) (2025)
- [Federated Learning for Computationally-Constrained Heterogeneous Devices: A Survey](https://mlsanity.com/paper/2307.09182/) (2023)
- [A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays](https://mlsanity.com/paper/2110.10486/) (2021)
- [Neural Preset for Color Style Transfer](https://mlsanity.com/paper/2303.13511/) (2023)
- [Fully Autonomous Programming with Large Language Models](https://mlsanity.com/paper/2304.10423/) (2023)
- [Efficient Fine-Tuning of BERT Models on the Edge](https://mlsanity.com/paper/2205.01541/) (2022)
- [Machine Learning for Microcontroller-Class Hardware: A Review](https://mlsanity.com/paper/2205.14550/) (2022)
- [EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation](https://mlsanity.com/paper/2202.07959/) (2022)
- [Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences](https://mlsanity.com/paper/2310.04621/) (2023)
- [On-device Training: A First Overview on Existing Systems](https://mlsanity.com/paper/2212.00824/) (2022)
- [Multisize Dataset Condensation](https://mlsanity.com/paper/2403.06075/) (2024)
- [Xiaomi MiMo-VL-Miloco Technical Report](https://mlsanity.com/paper/2512.17436/) (2025)
- [Asynchronous Federated Learning for Sensor Data with Concept Drift](https://mlsanity.com/paper/2109.00151/) (2021)
- [Training Machine Learning models at the Edge: A Survey](https://mlsanity.com/paper/2403.02619/) (2024)
- [DISTREAL: Distributed Resource-Aware Learning in Heterogeneous Systems](https://mlsanity.com/paper/2112.08761/) (2021)
- [Device-Cloud Collaborative Recommendation via Meta Controller](https://mlsanity.com/paper/2207.03066/) (2022)
- [On-Device Unsupervised Image Segmentation](https://mlsanity.com/paper/2303.12753/) (2023)
- [Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflows](https://mlsanity.com/paper/2201.07677/) (2022)
- [CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantization](https://mlsanity.com/paper/2203.05468/) (2022)
- [Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference](https://mlsanity.com/paper/2404.03085/) (2024)
- [HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Merging](https://mlsanity.com/paper/2507.17706/) (2025)
- [Integrating Pre-Trained Language Model with Physical Layer Communications](https://mlsanity.com/paper/2402.11656/) (2024)
- [Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning](https://mlsanity.com/paper/2505.05086/) (2025)
- [An Energy-Efficient Edge Computing Paradigm for Convolution-based Image Upsampling](https://mlsanity.com/paper/2107.07647/) (2021)
- [A Thorough Performance Benchmarking on Lightweight Embedding-based Recommender Systems](https://mlsanity.com/paper/2406.17335/) (2024)
- [Stepping Forward on the Last Mile](https://mlsanity.com/paper/2411.04036/) (2024)
- [Resource-Efficient Federated Fine-Tuning Large Language Models for Heterogeneous Data](https://mlsanity.com/paper/2503.21213/) (2025)
- [Efficient Compositional Multi-tasking for On-device Large Language Models](https://mlsanity.com/paper/2507.16083/) (2025)

## Abstract (arXiv)

The predominant paradigm for using machine learning models on a device is to train a model in the cloud and perform inference using the trained model on the device. However, with increasing number of smart devices and improved hardware, there is interest in performing model training on the device. Given this surge in interest, a comprehensive survey of the field from a device-agnostic perspective sets the stage for both understanding the state-of-the-art and for identifying open challenges and future avenues of research. However, on-device learning is an expansive field with connections to a large number of related topics in AI and machine learning (including online learning, model adaptation, one/few-shot learning, etc.). Hence, covering such a large number of topics in a single survey is impractical. This survey finds a middle ground by reformulating the problem of on-device learning as resource constrained learning where the resources are compute and memory. This reformulation allows tools, techniques, and algorithms from a wide variety of research areas to be compared equitably. In addition to summarizing the state-of-the-art, the survey also identifies a number of challenges and next steps for both the algorithmic and theoretical aspects of on-device learning.