Conditional Mutual Information and Information-Theoretic Phases of Decohered Gibbs States
Yifan Zhang, Sarang Gopalakrishnan

TL;DR
This paper investigates how local dissipation affects the emergence of long-range conditional mutual information in Gibbs states, revealing conditions for phase transitions and long-range correlations in quantum and classical systems.
Contribution
It provides the first rigorous analysis of conditions under which dissipation induces long-range CMI in Gibbs states, highlighting phase transitions at finite temperature.
Findings
Exponential decay of CMI in high-temperature Gibbs states with local dissipation.
Low-temperature hidden Markov networks can sustain long-range CMI.
Existence of finite-temperature information-theoretic phase transitions without thermodynamic phase transitions.
Abstract
Classical and quantum Markov networks -- including Gibbs states of commuting local Hamiltonians -- are characterized by the vanishing of conditional mutual information (CMI) between spatially separated subsystems. Adding local dissipation to a Markov network turns it into a \emph{hidden Markov network}, in which CMI is not guaranteed to vanish even at long distances. The onset of long-range CMI corresponds to an information-theoretic mixed-state phase transition, with far-ranging implications for teleportation, decoding, and state compressions. Little is known, however, about the conditions under which dissipation can generate long-range CMI. In this work we provide the first rigorous results in this direction. We establish that CMI in high-temperature Gibbs states subject to local dissipation decays exponentially, (i) for classical Hamiltonians subject to arbitrary local transition…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNeural Networks and Applications · Statistical Mechanics and Entropy
