Two-stage relaxation of operators through domain wall and magnon dynamics

TL;DR

This paper investigates the two-stage relaxation process of the out-of-time ordered correlator (OTOC) in local quantum circuits, revealing how domain wall and magnon dynamics govern the decay towards equilibrium.

Contribution

It introduces a systematic framework based on an emergent statistical model to explain the two-stage OTOC relaxation via domain wall and magnon modes, extending to Floquet models.

Findings

Identification of two distinct relaxation stages with different timescales.

Demonstration that domain wall and magnon modes control decay rates.

Extension of results from random circuits to Floquet models.

Abstract

The out-of-time ordered correlator (OTOC) has become a popular probe for quantum information spreading and thermalization. In systems with local interactions, the OTOC defines a characteristic butterfly lightcone that separates a regime not yet disturbed by chaos from one where time-evolved operators and the OTOC approach their equilibrium value. This relaxation has been shown to proceed in two stages, with the first stage exhibiting an extensive timescale and a decay rate slower than the gap of the transfer matrix -- known as the ``phantom eigenvalue". In this work, we investigate the two-stage relaxation of the OTOC towards its equilibrium value in various local quantum circuits. We apply a systematic framework based on an emergent statistical model, where the dynamics of two single-particle modes -- a domain wall and a magnon -- govern the decay rates. Specifically, a configuration with coexisting domain wall and magnon modes generates the phantom rate in the first stage, and competition between these modes determines the second stage. We also examine this relaxation within the operator cluster picture. The magnon modes translates into a bound state of clusters and domain wall into a random operator, giving consistent rates. Finally, we extend our findings from random in time circuits to a broad class of Floquet models.