Rademacher complexity for Markov chains: Applications to kernel smoothing and Metropolis–Hastings [PDF]
Following the seminal approach by Talagrand, the concept of Rademacher complexity for independent sequences of random variables is extended to Markov chains.
P. Bertail, Franccois Portier
semanticscholar +1 more source
Monotone bivariate Markov kernels with specified marginals [PDF]
Summary: Given two Markov kernels \( k\) and \( k'\) on an ordered Polish space, such that \( k\) is stochastically dominated by \( k'\), we establish the existence of: (i) a monotone bivariate Markov kernel whose marginals are \( k\) and \( k'\) and (ii) an upward coupler from \( k\) to \( k'\). This extends the results of \textit{V.
Machida, Motoya, Shibakov, Alexander
openaire +1 more source
Unsupervised SAR image segmentation based on kernel TMFs with belief propagation
The triplet Markov field (TMF) model has achieved promising results in synthetic aperture radar (SAR) image segmentation. Focusing on the simple likelihood modelling of an SAR image and the effective optimisation of the TMF model, an unsupervised SAR ...
Lu Gan, Xiaoming Liu, Ziwei Li
doaj +1 more source
The Hypergroup Property and Representation of Markov Kernels [PDF]
accept\'e au "S\'eminaire de Probabilit\'es"
Bakry, Dominique, Huet, Nolwen
openaire +3 more sources
Calculating principal eigen-functions of non-negative integral kernels: particle approximations and applications [PDF]
Often in applications such as rare events estimation or optimal control it is required that one calculates the principal eigen-function and eigen-value of a non-negative integral kernel.
Kantas, Nikolas, Whiteley, Nick
core +3 more sources
Memory kernel approach to generalized Pauli channels: Markovian, semi-Markov, and beyond [PDF]
In this paper, we analyze the evolution of the generalized Pauli channels governed by the memory kernel master equation. We provide necessary and sufficient conditions for the memory kernel to give rise to the legitimate (completely positive and trace ...
Katarzyna Siudzi'nska, D. Chru'sci'nski
semanticscholar +1 more source
Non ultracontractive heat kernel bounds by Lyapunov conditions [PDF]
Nash and Sobolev inequalities are known to be equivalent to ultracontractive properties of heat-like Markov semigroups, hence to uniform on-diagonal bounds on their kernel densities.
Bolley, François +2 more
core +3 more sources
Transformation of Hand-Shape Features for a Biometric Identification Approach
The present work presents a biometric identification system for hand shape identification. The different contours have been coded based on angular descriptions forming a Markov chain descriptor.
Jesús B. Alonso +2 more
doaj +1 more source
Time inhomogeneous Markov chains with wave-like behavior
Starting from a given Markov kernel on a finite set $V$ and a bijection $g$ of $V$, we construct and study a time inhomogeneous Markov chain whose kernel at time $n$ is obtained from $K$ by transport of $g^{n-1}$.
Saloff-Coste, L., Zúñiga, J.
core +1 more source
Stochastic monotonicity and duality for one-dimensional Markov processes [PDF]
The theory of monotonicity and duality is developed for general one-dimensional Feller processes, extending the approach from [11]. Moreover it is shown that local monotonicity conditions (conditions on the Lévy kernel) are sufficient to prove the well-
Kolokoltsov, V. N. (Vasiliĭ Nikitich)
core +1 more source

