# Computing Low-Entropy Couplings for Large-Support Distributions

arXiv: https://arxiv.org/abs/2405.19540 · HTML: https://mlsanity.com/paper/2405.19540/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2024.

## Built on by (most cited first, 1 of 1)

- [Learning from Totally Unpaired Data via Minimum Conditional Entropy Coupling](https://mlsanity.com/paper/2605.16229/) (2026)

## Abstract (arXiv)

Minimum-entropy coupling (MEC) -- the process of finding a joint distribution with minimum entropy for given marginals -- has applications in areas such as causality and steganography. However, existing algorithms are either computationally intractable for large-support distributions or limited to specific distribution types and sensitive to hyperparameter choices. This work addresses these limitations by unifying a prior family of iterative MEC (IMEC) approaches into a generalized partition-based formalism. From this framework, we derive a novel IMEC algorithm called ARIMEC, capable of handling arbitrary discrete distributions, and introduce a method to make IMEC robust to suboptimal hyperparameter settings. These innovations facilitate the application of IMEC to high-throughput steganography with language models, among other settings. Our codebase is available at https://github.com/ssokota/mec .