A Transport-Information Framework for Continuous-Fiber-Aligned Coarse-Graining Representation Sets
Abstract
Consider representation sets of interest whose elements are associated with continuous realizations related to them through coarse-graining (CG). CG can be regarded as an operation that reduces a representation by discarding information that is not retained in its output. However, a systematic description of the information structure associated with CG in general remains to be established. Here, we propose a transport-information framework for continuous-fiber-aligned representation sets, in which each representation is associated with a continuous realization through a fiber structure, with CG defining the projection onto the representation. Within this framework, CG is described through a local-map operation that transports continuous probability mass onto representative points. The resulting transport cost is expressed as the contraction of the second-moment structure of the underlying continuous representation with the transport metric. Building on the previously proposed framework of unavoidable canonical nonlinearity (UCN), this construction provides a non-arbitrary information-theoretic interpretation of the CG-associated transport cost in terms of information indistinguishability, quantified by an expected second-order structure on statistical manifold associated with the CG geometry. We also show that the proposed framework can also be naturally extended to the CG of the discrete measures themselves. The present framework provides a basis for describing information costs associated with individual CG operations and for comparing representation sets while accounting for their underlying continuous realizations.
Related
- Representation-Aware Transport-Information Measure for Non-inclusive Discrete Supports
- A wave-particle decomposition framework for multiscale kinetic transport: continuous-spectrum equations and coupled wave-particle iteration
- Quantum Kolmogorov--Arnold representation theorem for continuous unitary-valued maps
- A continuous-mode quantum-optical representation of finite strong-field laser pulses in free space
- Neural Information Causality: A Random-Access Capacity Law for Representation Learning
BibTeX
@misc{yuge2026transportinformation,
title = {{A Transport-Information Framework for Continuous-Fiber-Aligned Coarse-Graining Representation Sets}},
author = {Koretaka Yuge},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.27811},
eprint = {2610.27811},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.27811},
}
RIS
TY - UNPB
TI - A Transport-Information Framework for Continuous-Fiber-Aligned Coarse-Graining Representation Sets
AU - Koretaka Yuge
PY - 2026
DA - 2026/10/28
PB - arXiv
DO - 10.48550/arxiv.2610.27811
UR - https://arxiv.org/abs/2610.27811
AB - Consider representation sets of interest whose elements are associated with continuous realizations related to them through coarse-graining (CG). CG can be regarded as an operation that reduces a representation by discarding information that is not retained in its output. However, a systematic description of the information structure associated with CG in general remains to be established. Here, we propose a transport-information framework for continuous-fiber-aligned representation sets, in which each representation is associated with a continuous realization through a fiber structure, with CG defining the projection onto the representation. Within this framework, CG is described through a local-map operation that transports continuous probability mass onto representative points. The resulting transport cost is expressed as the contraction of the second-moment structure of the underlying continuous representation with the transport metric. Building on the previously proposed framework of unavoidable canonical nonlinearity (UCN), this construction provides a non-arbitrary information-theoretic interpretation of the CG-associated transport cost in terms of information indistinguishability, quantified by an expected second-order structure on statistical manifold associated with the CG geometry. We also show that the proposed framework can also be naturally extended to the CG of the discrete measures themselves. The present framework provides a basis for describing information costs associated with individual CG operations and for comparing representation sets while accounting for their underlying continuous realizations.
ER -