English

P$^2$U: Progressive Precision Update For Efficient Model Distribution

Machine Learning 2025-07-01 v1 Multimedia

Abstract

Efficient model distribution is becoming increasingly critical in bandwidth-constrained environments. In this paper, we propose a simple yet effective approach called Progressive Precision Update (P2^2U) to address this problem. Instead of transmitting the original high-precision model, P2^2U transmits a lower-bit precision model, coupled with a model update representing the difference between the original high-precision model and the transmitted low precision version. With extensive experiments on various model architectures, ranging from small models (161 - 6 million parameters) to a large model (more than 100100 million parameters) and using three different data sets, e.g., chest X-Ray, PASCAL-VOC, and CIFAR-100, we demonstrate that P2^2U consistently achieves better tradeoff between accuracy, bandwidth usage and latency. Moreover, we show that when bandwidth or startup time is the priority, aggressive quantization (e.g., 4-bit) can be used without severely compromising performance. These results establish P2^2U as an effective and practical solution for scalable and efficient model distribution in low-resource settings, including federated learning, edge computing, and IoT deployments. Given that P2^2U complements existing compression techniques and can be implemented alongside any compression method, e.g., sparsification, quantization, pruning, etc., the potential for improvement is even greater.

Keywords

Cite

@article{arxiv.2506.22871,
  title  = {P$^2$U: Progressive Precision Update For Efficient Model Distribution},
  author = {Homayun Afrabandpey and Hamed Rezazadegan Tavakoli},
  journal= {arXiv preprint arXiv:2506.22871},
  year   = {2025}
}
R2 v1 2026-07-01T03:37:48.735Z