3 papers
math.PR2026
Spectral Purification in Reversible Markov Chains: Hidden Parameters, Observable Equivalence, and Finite-Time Rigidity
Qiao Wang
Classical spectral theory of reversible Markov chains characterizes the asymptotic relaxation dominated by the slowest eigenmode, governed by the spectral gap. This paper studies a…
stat.ML2026
Expectation-Maximization as a Spectrally Governed Relaxation Flow
Qiao Wang
The expectation--maximization (EM) algorithm combines global monotonicity, local linear convergence, and strong practical robustness, but these features are usually analyzed separa…
cs.IT2026
Relaxation Kernel, Spectral Dissipation, and Global Convergence of Blahut--Arimoto Dynamics
Qiao Wang
We develop a spectral theory for continuous- and discrete-time Blahut--Arimoto (BA) dynamics, centered on the relaxation kernel $ \G = \E_p[K^*_X \otimes K^*_X] $. Five main result…