English
Related papers

Related papers: Stochastic approximation in non-markovian environm…

200 papers

Neural ordinary differential equations offer an effective framework for modeling dynamical systems by learning a continuous-time vector field. However, they rely on the Markovian assumption - that future states depend only on the current…

Machine Learning · Computer Science 2025-09-16 Eliott Pradeleix , Rémy Hosseinkhan-Boucher , Alena Shilova , Onofrio Semeraro , Lionel Mathelin

We introduce and analyze a new class of monotone stochastic recursions in a regenerative environment which is essentially broader than that of Markov chains. We prove stability theorems and apply our results {to three canonical models in…

Probability · Mathematics 2022-02-22 Sergey Foss , Vsevolod Shneer , Jonathan P. Thomas , Tim Worrall

Modeling car-following behavior is fundamental to microscopic traffic simulation, yet traditional deterministic models often fail to capture the full extent of variability and unpredictability in human driving. While many modern approaches…

Applications · Statistics 2026-01-30 Chengyuan Zhang , Zhengbing He , Cathy Wu , Lijun Sun

Non-Markovian models have great expressive power, at the cost of complex analysis of the stochastic process. The method of Stochastic State Classes (SSCs) derives closed-form analytical expressions for the joint Probability Density…

Logic in Computer Science · Computer Science 2024-10-24 Gabriel Dengler , Laura Carnevali , Carlos E. Budde , Enrico Vicario

A stochastic representation of the dynamics of open quantum systems, suitable for non-perturbative system-reservoir interaction, non-Markovian effects and arbitrarily driven systems is presented. It includes the case of driving on…

Statistical Mechanics · Physics 2016-10-05 Jürgen T. Stockburger

We review the most recent developments in the theory of open quantum systems focusing on situations in which the reservoir memory effects, due to long-lasting and non-negligible correlations between system and environment, play a crucial…

Quantum Physics · Physics 2014-03-11 Pinja Haikka , Sabrina Maniscalco

In this paper, we investigate the exponential ergodicity in a Wasserstein-type distance for a damping Hamiltonian dynamics with state-dependent and non-local collisions, which indeed is a special case of piecewise deterministic Markov…

Probability · Mathematics 2022-04-05 Jianhai Bao , Jian Wang

Reinforcement learning in non-stationary environments is challenging due to abrupt and unpredictable changes in dynamics, often causing traditional algorithms to fail to converge. However, in many real-world cases, non-stationarity has some…

Machine Learning · Computer Science 2025-03-25 Mohsen Amiri , Sindri Magnússon

Stochastic exclusion processes play an integral role in the physics of non-equilibrium statistical mechanics. These models are Markovian processes, described by a classical master equation. In this paper a quantum mechanical version of a…

Quantum Physics · Physics 2015-03-13 Kristan Temme , Michael M. Wolf , Frank Verstraete

This work tackles the problem of robust zero-shot planning in non-stationary stochastic environments. We study Markov Decision Processes (MDPs) evolving over time and consider Model-Based Reinforcement Learning algorithms in this setting.…

Machine Learning · Computer Science 2020-01-16 Erwan Lecarpentier , Emmanuel Rachelson

Although stochastic approximation learning methods have been widely used in the machine learning literature for over 50 years, formal theoretical analyses of specific machine learning algorithms are less common because stochastic…

Machine Learning · Statistics 2017-04-21 Richard M. Golden

We study the ergodic behaviour of a discrete-time process $X$ which is a Markov chain in a stationary random environment. The laws of $X_t$ are shown to converge to a limiting law in (weighted) total variation distance as $t\to\infty$.…

Probability · Mathematics 2019-07-29 Balazs Gerencser , Miklos Rasonyi

We develop a model-free approach to optimally control stochastic, Markovian systems subject to a reach-avoid constraint. Specifically, the state trajectory must remain within a safe set while reaching a target set within a finite time…

Optimization and Control · Mathematics 2025-09-30 Tingting Ni , Maryam Kamgarpour

We study the consequences of adopting the memory dependent, non-Markovian, physics with the memory-less over-damped approximation usually employed to investigate Brownian particles. Due to the finite correlation time scale associated with…

Statistical Mechanics · Physics 2019-02-05 Eduardo dos S. Nascimento , Welles A. M. Morgado

Autoregressive generative models -- including Transformers, recurrent neural networks, classical Kalman filters, state space models, and Mamba -- all generate sequences by sampling each output from a deterministic summary of the past,…

Statistical Mechanics · Physics 2026-04-17 Takahiro Sagawa

This paper focuses on time-varying delayed stochastic differential systems with stochastically switching parameters formulated by a unified switching behavior combining a discrete adapted process and a Cox process. Unlike prior studies…

Dynamical Systems · Mathematics 2024-01-30 Xinyu Wu , Zidong Wang , Wenlian Lu

We develop a theory of ergodicity for a class of random dynamical systems where the driving noise is not white. The two main tools of our analysis are the strong Feller property and topological irreducibility, introduced in this work for a…

Probability · Mathematics 2011-11-09 M. Hairer , A. Ohashi

Non-Markovian effects arising in open quantum systems evolution have been a subject of increasing interest over the past decade. One of the most appealing features of non-Markovianity (NM) is that it captures scenarios where loss of…

Quantum Physics · Physics 2017-08-02 P. M. Poggi , F. C. Lombardo , D. A. Wisniacki

This work introduces a non-intrusive model reduction approach for learning reduced models from partially observed state trajectories of high-dimensional dynamical systems. The proposed approach compensates for the loss of information due to…

Machine Learning · Computer Science 2021-03-29 Wayne Isaac Tan Uy , Benjamin Peherstorfer

Stochastic gradient optimization is the dominant learning paradigm for a variety of scenarios, from classical supervised learning to modern self-supervised learning. We consider stochastic gradient algorithms for learning problems whose…

Machine Learning · Statistics 2025-08-29 Facheng Yu , Ronak Mehta , Alex Luedtke , Zaid Harchaoui