Stochastic Orders of the Exit Pair and the Monotone Response to Resetting
Tony Newton, Juan Antonio Vega Coso
Abstract
Resetting a process, that is, restarting it from its initial position at random times, changes the probability that it leaves an interval through one end rather than the other. We show that the direction of this change is governed by how the exit time depends on the exit side, and we express this through classical stochastic orders. For random walks and birth-death chains we determine when resetting more intensively always moves the exit probability in the same direction, and we show that this can fail: we give an explicit chain in which the direction reverses twice over time, and bound the number of such reversals spectrally. We also show how the direction depends on the starting point. In the continuum limit we obtain the corresponding results for diffusions with drift.
Create a lesson
Related papers
Almost sure exponential stability of multi-dimensional stochastic systems driven by a symmetric α-stable process
Xuekang Zhang, Hongjian Liu, Guangjun Shen
The Arc Threshold of the Two-Row Ising Torus: Exact Factorization, an Algebraic Critical Coupling, Uniformity in the Circumference, and the Rate of Convergence
Marco Mandap
Markovian Lifts and Multifactor Approximations for Weighted Sub-fractional Brownian Motion
J. H. Ramirez-Gonzalez, Edison Cuba
Rényi mixing bounds for kinetic samplers via L2 hypocoercivity
Jianfeng Lu, Yinchen Luo
Bayesian Filters via the Stochastic Category
Kenichi Bannai, Masahiro Kurisaki
Synchronization of Enriched Spin Glasses
Franziska Engler, Justin Ko