English
Related papers

Related papers: Ergodic-risk Criterion for Stochastically Stabiliz…

200 papers

In this contribution, we derive ILEG, an iterative algorithm to find risk sensitive solutions to nonlinear, stochastic optimal control problems. The algorithm is based on a linear quadratic approximation of an exponential risk sensitive…

Systems and Control · Computer Science 2015-12-23 Farbod Farshidian , Jonas Buchli

This work concerns controlled Markov chains with finite state and action spaces. The transition law satisfies the simultaneous Doeblin condition, and the performance of a control policy is measured by the (long-run) risk-sensitive average…

Probability · Mathematics 2007-05-23 Rolando Cavazos-Cadena , Daniel Hernandez-Hernandez

Using small noise limit approach, we study degenerate stochastic ergodic control problems and as a byproduct obtain error bounds for the $\varepsilon$-optimal controls. We also establish tunneling for a special ergodic control problem and…

Optimization and Control · Mathematics 2024-05-02 K. Suresh Kumar , Vikrant Desai

In this article we consider the ergodic risk-sensitive control problem for a large class of multidimensional controlled diffusions on the whole space. We study the minimization and maximization problems under either a blanket stability…

Optimization and Control · Mathematics 2021-01-01 Ari Arapostathis , Anup Biswas , Somnath Pradhan

Non-reversible Markov chain Monte Carlo schemes based on piecewise deterministic Markov processes have been recently introduced in applied probability, automatic control, physics and statistics. Although these algorithms demonstrate…

Computation · Statistics 2017-08-29 George Deligiannidis , Alexandre Bouchard-Côté , Arnaud Doucet

An optimal ergodic control problem (EC problem, for short) is investigated for a linear stochastic differential equation with quadratic cost functional. Constant nonhomogeneous terms, not all zero, appear in the state equation, which lead…

Optimization and Control · Mathematics 2020-04-24 Hongwei Mei , Qingmeng Wei , Jiongmin Yong

We study the estimation of the value function for continuous-time Markov diffusion processes using a single, discretely observed ergodic trajectory. Our work provides non-asymptotic statistical guarantees for the least-squares…

Machine Learning · Computer Science 2025-02-07 Wenlong Mou

We study the limit behaviour of a generally non-linear ordinary differential equation whose solution is a superadditive generalisation of a stochastic matrix, and provide necessary and sufficient conditions for this solution to be ergodic,…

Probability · Mathematics 2016-09-21 Jasper De Bock

We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by "controlled" Markov noise. In particular, the faster and slower recursions have non-additive controlled Markov noise…

Machine Learning · Computer Science 2020-12-03 Prasenjit Karmakar

We develop a central limit theorem (CLT) for a non-parametric estimator of the transition matrices in controlled Markov chains (CMCs) with finite state-action spaces. Our results establish precise conditions on the logging policy under…

Statistics Theory · Mathematics 2026-03-26 Ziwei Su , Imon Banerjee , Diego Klabjan

We introduce the Lyapunov approach to optimal control problems of average risk-sensitive Markov control processes with general risk maps. Motivated by applications in particular to behavioral economics, we consider possibly non-convex risk…

Optimization and Control · Mathematics 2015-07-23 Yun Shen , Klaus Obermayer , Wilhelm Stannat

Trajectory optimization is a fundamental stochastic optimal control problem. This paper deals with a trajectory optimization approach for dynamical systems subject to measurement noise that can be fitted into linear time-varying stochastic…

Systems and Control · Electrical Eng. & Systems 2021-08-24 Prakash Mallick , Zhiyong Chen

We study nonzero-sum stochastic games for continuous time Markov chains on a denumerable state space with risk sensitive discounted and ergodic cost criteria. For the discounted cost criterion we first show that the corresponding system of…

Optimization and Control · Mathematics 2016-03-09 Mrinal K. Ghosh , K. Suresh Kumar , Chandan Pal

The use of higher-order stochastic processes such as nonlinear Markov chains or vertex-reinforced random walks is significantly growing in recent years as they are much better at modeling high dimensional data and nonlinear dynamics in…

Numerical Analysis · Mathematics 2020-04-29 Dario Fasino , Francesco Tudisco

We study infinite horizon discounted-cost and ergodic-cost risk-sensitive zero-sum stochastic games for controlled continuous time Markov chains on a countable state space. For the discounted-cost game we prove the existence of value and…

Optimization and Control · Mathematics 2016-03-09 Mrinal K. Ghosh , K. Suresh Kumar , Chandan Pal

The goal of this paper is to develop a general method to establish conditional ergodicity of infinite-dimensional Markov chains. Given a Markov chain in a product space, we aim to understand the ergodic properties of its conditional…

Probability · Mathematics 2014-10-28 Xin Thomson Tong , Ramon van Handel

In this paper, we consider a class of stochastic optimal control problems with risk constraints that are expressed as bounded probabilities of failure for particular initial states. We present here a martingale approach that diffuses a risk…

Systems and Control · Computer Science 2015-07-09 Vu Anh Huynh , Leonid Kogan , Emilio Frazzoli

In this work, we establish risk bounds for the Empirical Risk Minimization (ERM) with both dependent and heavy-tailed data-generating processes. We do so by extending the seminal works of Mendelson [Men15, Men18] on the analysis of ERM with…

Statistics Theory · Mathematics 2021-09-14 Abhishek Roy , Krishnakumar Balasubramanian , Murat A. Erdogdu

We derive the explicit solutions to singular stochastic control problems of the monotone follower type with (a) an expected discounted criterion, (b) an expected ergodic criterion and (c) a pathwise ergodic criterion. These problems have…

Optimization and Control · Mathematics 2025-02-05 Gechun Liang , Zhesheng Liu , Mihail Zervos

This paper studies the exponential stability of random matrix products driven by a general (possibly unbounded) state space Markov chain. It is a cornerstone in the analysis of stochastic algorithms in machine learning (e.g. for parameter…

Machine Learning · Statistics 2021-02-02 Alain Durmus , Eric Moulines , Alexey Naumov , Sergey Samsonov , Hoi-To Wai