English

Radio: Rate-Distortion Optimization for Large Language Model Compression

Machine Learning 2025-05-07 v1 Computation and Language

Abstract

In recent years, the compression of large language models (LLMs) has emerged as a key problem in facilitating LLM deployment on resource-limited devices, reducing compute costs, and mitigating the environmental footprint due to large-scale AI infrastructure. Here, we establish the foundations of LLM quantization from a rate-distortion theory perspective and propose a quantization technique based on simple rate-distortion optimization. Our technique scales to models containing hundreds of billions of weight parameters and offers users the flexibility to compress models, post-training, to a model size or accuracy specified by the user.

Keywords

Cite

@article{arxiv.2505.03031,
  title  = {Radio: Rate-Distortion Optimization for Large Language Model Compression},
  author = {Sean I. Young},
  journal= {arXiv preprint arXiv:2505.03031},
  year   = {2025}
}

Comments

Accepted to ICML 2025

R2 v1 2026-06-28T23:22:08.613Z