Reversible Markov chains possess finite-time spectral rigidity controlled by eigenvalue separation, with two-sided bounds on rigidity time and a covariance-based spectral entropy theory.
Relaxation Kernel and Global Convergence of the Blahut-Arimoto Dynamics
2 Pith papers cite this work. Polarity classification is still indexing.
abstract
Motivated by a continuous-time formulation of the Blahut-Arimoto scheme, we study a nonlinear dissipative flow on the probability simplex generated by a Gibbs-type self-consistent evolution. We establish an exact dissipation identity showing that the free energy decreases according to a weighted $\chi^2$-type fluctuation, yielding an explicit entropy-production formula for the nonlinear dynamics. Linearization around a nondegenerate stationary state reveals that the same fluctuation is governed by a symmetric positive semidefinite relaxation kernel built from equilibrium conditional covariances. This kernel determines both the local linearized flow and the quadratic expansion of the free energy. We further show that it coincides with the Fisher-Rao Hessian of the free energy at equilibrium,so that its spectral gap characterizes the local relaxation rate. Combining the exact dissipation identity with local spectral contraction, we obtain convergence of the flow toward equilibrium within the connected component of a nondegenerate stationary state. In the Gaussian quadratic case, the dynamics admits an explicit finite-dimensional reduction for which the relaxation kernel, spectral gap, and asymptotic relaxation law can be computed in closed form. These results identify a common structure linking entropy dissipation, local equilibrium geometry, and spectral relaxation in a class of nonlinear Gibbs-type probability flows.
citation-role summary
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
EM's monotonicity and local rate are unified by the spectral operator G = I - DT that equals the missing-information ratio and observed-likelihood Hessian, enabling accelerated local updates.
citing papers explorer
-
Quantitative Spectral Rigidity and Finite-Time Spectral Thermodynamics in Reversible Markov Chains
Reversible Markov chains possess finite-time spectral rigidity controlled by eigenvalue separation, with two-sided bounds on rigidity time and a covariance-based spectral entropy theory.
-
Expectation-Maximization as a Spectrally Governed Relaxation Flow
EM's monotonicity and local rate are unified by the spectral operator G = I - DT that equals the missing-information ratio and observed-likelihood Hessian, enabling accelerated local updates.