Saved in:
Bibliographic Details
Main Authors: Nguyen, Nam, Tavakoli, Hassan, Vuong, An, Nguyen, Thinh, Bose, Bella
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.09833
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918493833658368
author Nguyen, Nam
Tavakoli, Hassan
Vuong, An
Nguyen, Thinh
Bose, Bella
author_facet Nguyen, Nam
Tavakoli, Hassan
Vuong, An
Nguyen, Thinh
Bose, Bella
contents This paper studies cross-domain lossy compression through the lens of minimum entropy coupling (MEC) with rate and classification constraints. In this setting, an encoder observes samples from a degraded source domain, while the decoder is required to generate outputs following a prescribed target distribution and to preserve information relevant to a downstream classification task. Motivated by logarithmic-loss distortion, we adopt an information-based objective that maximizes the coupling strength between the source and reconstruction, rather than minimizing a sample-wise distortion. Under common randomness, we formulate a rate-constrained MEC problem (MEC-B) and show that the intermediate representation can be removed without loss of optimality, yielding an equivalent deterministic coupling formulation. For Bernoulli sources, closed-form expressions are derived with and without classification constraints. In addition, we implement a neural restoration framework using quantization, entropy modeling, distribution matching, and classification regularization. Experiments on MNIST super-resolution and SVHN denoising show that increasing the available rate improves classification accuracy and yields more informative reconstructions.
format Preprint
id arxiv_https___arxiv_org_abs_2605_09833
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cross-Domain Lossy Compression via Constrained Minimum Entropy Coupling
Nguyen, Nam
Tavakoli, Hassan
Vuong, An
Nguyen, Thinh
Bose, Bella
Information Theory
Machine Learning
This paper studies cross-domain lossy compression through the lens of minimum entropy coupling (MEC) with rate and classification constraints. In this setting, an encoder observes samples from a degraded source domain, while the decoder is required to generate outputs following a prescribed target distribution and to preserve information relevant to a downstream classification task. Motivated by logarithmic-loss distortion, we adopt an information-based objective that maximizes the coupling strength between the source and reconstruction, rather than minimizing a sample-wise distortion. Under common randomness, we formulate a rate-constrained MEC problem (MEC-B) and show that the intermediate representation can be removed without loss of optimality, yielding an equivalent deterministic coupling formulation. For Bernoulli sources, closed-form expressions are derived with and without classification constraints. In addition, we implement a neural restoration framework using quantization, entropy modeling, distribution matching, and classification regularization. Experiments on MNIST super-resolution and SVHN denoising show that increasing the available rate improves classification accuracy and yields more informative reconstructions.
title Cross-Domain Lossy Compression via Constrained Minimum Entropy Coupling
topic Information Theory
Machine Learning
url https://arxiv.org/abs/2605.09833