English
Related papers

Related papers: Moderate Deviation Principles for Weakly Interacti…

200 papers

Noisy sensing, imperfect control, and environment changes are defining characteristics of many real-world robot tasks. The partially observable Markov decision process (POMDP) provides a principled mathematical framework for modeling and…

Robotics · Computer Science 2022-09-22 Mikko Lauri , David Hsu , Joni Pajarinen

Recent attention in quickest change detection in the multi-sensor setting has been on the case where the densities of the observations change at the same instant at all the sensors due to the disruption. In this work, a more general…

Information Theory · Computer Science 2016-11-18 Vasanthan Raghavan , Venugopal V. Veeravalli

The inference of Markov models from data on stochastic dynamical trajectories over the large time-window $T$ is revisited via the Large Deviations at Level 2.5 for the time-empirical density and the time-empirical flows. The goal is to…

Statistical Mechanics · Physics 2021-07-01 Cecile Monthus

We consider oscillatory systems of interacting Hawkes processes introduced in Ditlevsen and Loecherbach (2017) to model multi-class systems of interacting neurons together with the diffusion approximations of their intensity processes. This…

Probability · Mathematics 2017-09-28 Eva Löcherbach

We consider a class of discrete $q$-state spin models defined in terms of a translation-invariant quasilocal specification with discrete clock-rotation invariance which have extremal Gibbs measures $\mu'_{\varphi}$ labeled by the…

Probability · Mathematics 2014-09-15 Benedikt Jahnel , Christof Külske

Langevin Dynamics is a Stochastic Differential Equation (SDE) central to sampling and generative modeling and is implemented via time discretization. Langevin Monte Carlo (LMC), based on the Euler-Maruyama discretization, is the simplest…

Machine Learning · Computer Science 2025-10-10 Saravanan Kandasamy , Dheeraj Nagaraj

We introduce a framework for approximate analysis of Markov decision processes (MDP) with bounded-, unbounded-, and infinite-horizon properties. The main idea is to identify a "core" of an MDP, i.e., a subsystem where we provably remain…

Systems and Control · Electrical Eng. & Systems 2023-06-22 Jan Křetínský , Tobias Meggendorfer

Switching dynamical systems provide a powerful, interpretable modeling framework for inference in time-series data in, e.g., the natural sciences or engineering applications. Since many areas, such as biology or discrete-event systems, are…

Machine Learning · Computer Science 2021-09-30 Lukas Köhs , Bastian Alt , Heinz Koeppl

Markov decision processes (MDPs) are a standard model for sequential decision-making problems and are widely used across many scientific areas, including formal methods and artificial intelligence (AI). MDPs do, however, come with the…

Artificial Intelligence · Computer Science 2024-12-11 Marnix Suilen , Thom Badings , Eline M. Bovy , David Parker , Nils Jansen

Oscillatory systems of interacting Hawkes processes with Erlang memory kernels were introduced in Ditlevsen (2017). They are piecewise deterministic Markov processes (PDMP) and can be approximated by a stochastic diffusion. First, a strong…

Numerical Analysis · Mathematics 2020-03-25 Julien Chevallier , Anna Melnykova , Irene Tubikanec

We derive moderate deviation principles for the trajectory of the empirical magnetization of the standard Curie-Weiss model via a general analytic approach based on convergence of generators and uniqueness of viscosity solutions for…

Probability · Mathematics 2017-10-13 Francesca Collet , Richard Kraaij

Much work in the study of large deviations for random graph models is focused on the dense regime where the theory of graphons has emerged as a principal tool. These tools do not give a good approach to large deviation problems for random…

Probability · Mathematics 2020-07-07 Shankar Bhamidi , Amarjit Budhiraja , Paul Dupuis , Ruoyu Wu

This paper presents a state representation framework for Markov decision processes (MDPs) that can be learned solely from state trajectories, requiring neither reward signals nor the actions executed by the agent. We propose learning the…

Machine Learning · Computer Science 2026-03-25 Lorenzo Steccanella , Joshua B. Evans , Özgür Şimşek , Anders Jonsson

We present new algorithms for computing and approximating bisimulation metrics in Markov Decision Processes (MDPs). Bisimulation metrics are an elegant formalism that capture behavioral equivalence between states and provide strong…

Machine Learning · Computer Science 2019-11-22 Pablo Samuel Castro

Determinantal point processes (DPPs) are probabilistic models for repulsion. When used to represent the occurrence of random subsets of a finite base set, DPPs allow to model global negative associations in a mathematically elegant and…

Statistics Theory · Mathematics 2019-01-29 Kayvan Sadeghi , Alessandro Rinaldo

We consider weakly interacting diffusions on time varying random graphs. The system consists of a large number of nodes in which the state of each node is governed by a diffusion process that is influenced by the neighboring nodes. The…

Probability · Mathematics 2017-02-16 Shankar Bhamidi , Amarjit Budhiraja , Ruoyu Wu

Regime-switching processes contain two components: continuous component and discrete component, which can be used to describe a continuous dynamical system in a random environment. Such processes have many different properties than general…

Probability · Mathematics 2017-10-26 Jinghai Shao

Piecewise-deterministic Markov processes (PDMPs) offer a powerful stochastic modeling framework that combines deterministic trajectories with random perturbations at random times. Estimating their local characteristics (particularly the…

Methodology · Statistics 2025-12-29 Romain Azaïs , Solune Denis

Behind the nice unification provided by the notion of the level 2.5 in the field of large deviations for time-averages over a long Markov trajectory, there are nevertheless very important qualitative differences between the meaning of the…

Statistical Mechanics · Physics 2024-02-20 Cecile Monthus

We prove a large deviation principle on path space for a class of discrete time Markov processes whose state space is the intersection of a regular domain $\L\subset \R^d$ with some lattice of spacing $\e$. Transitions from $x$ to $y$ are…

Probability · Mathematics 2007-05-23 Anton Bovier , Veronique Gayrard
‹ Prev 1 8 9 10 Next ›