Radio: Rate–Distortion Optimization for Large Language Model Compression

Sean I. Young
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:72819-72836, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-young25b, title = {Radio: Rate–Distortion Optimization for Large Language Model Compression}, author = {Young, Sean I.}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {72819--72836}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/young25b/young25b.pdf}, url = {https://proceedings.mlr.press/v267/young25b.html}, 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.} }
Endnote
%0 Conference Paper %T Radio: Rate–Distortion Optimization for Large Language Model Compression %A Sean I. Young %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-young25b %I PMLR %P 72819--72836 %U https://proceedings.mlr.press/v267/young25b.html %V 267 %X 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.
APA
Young, S.I.. (2025). Radio: Rate–Distortion Optimization for Large Language Model Compression. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:72819-72836 Available from https://proceedings.mlr.press/v267/young25b.html.

Related Material