Stochastic Linear Dynamical Systems

Ask about this topic

Overview

Stochastic linear dynamical systems describe evolving states through linear transition rules with random disturbances, and are used in settings from sensor-based tracking to neural data and feedback control. Researchers estimate transition matrices and latent states from trajectories, often using least squares, moment methods, Bayesian or spectral approaches, and structural constraints to handle partial observations, missing data, or heavy-tailed noise. Control work uses these models for tasks such as chance-constrained planning and safe adaptive control, while switching models capture changes between dynamical regimes. A central challenge is obtaining reliable finite-sample guarantees when data are limited or noisy without making predictions or control overly conservative.

Latest papers

CardsList

20 papers6 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. Learning structured linear dynamical systems from missing observations

    Oct 8, 2026Aravinda Kanchana Ruwanpathirana, Hemant Tyagi, Sunny G. W. WangSystem IdentificationLearning with Missing Data

    Division of Mathematical Sciences, SPMS, NTU Singapore 637371

  2. Delay-coordinate reconstruction and conditional-moment causal diagnostics in stochastic systems

    Oct 4, 2026Jun OhkuboDynamical SystemsStochastic Linear Dynamical Systems

    Graduate School of Science and Engineering, Saitama University, Sakura, Saitama, 338–8570 Japan

  3. Inferring Multi-Timescale Neural Dynamics with Switching Linear Dynamical Systems

    Oct 1, 2026Lulu Gong, Yongxu Zhang, Shreya SaxenaStochastic Linear Dynamical SystemsLatent Dynamics Modeling

    Center for Neurocomputation and Machine Intelligence, Wu Tsai Institute, Department of Biomedical Engineering, Yale University, New Haven, CT 06510, USA

  4. Block Optimism for Nonstationary Bandits with Latent Linear Dynamics

    Oct 1, 2026Taehyun Hwang, Hyunjun Choi, Heesang Ann +1Multi-Armed BanditsStochastic Linear Dynamical Systems

    Seoul National University Soeul, South Korea

  5. Learning Linear Systems under Heavy-Tailed Noise: A Non-Asymptotic Analysis from A Single Trajectory

    Sep 30, 2026Xiaomian Yang, Sungho ShinStochastic Linear Dynamical SystemsSample Complexity

    Department of Chemical Engineering Massachusetts Institute of Technology Cambridge, MA 02139

  6. Accelerated surrogate dynamics for dynamical, stochastic system evolution

    Sep 29, 2026Marco Jochum, Ioannis Kouroudis, Gohar Ali Siddiqui +3Neural Surrogate ModelingDynamical Systems

    Chair of Simulation of Nanosystems for Energy Conversion, Department of Electrical Engineering, TUM School of Computation, Information and Technology, Atomistic Modeling Center (AMC), Munich Data Science Institute (MDSI), Technical University of Munich, Hans-Piloty-Straße 1, 85748 Garching, Germany

  7. One Intervention per Component is Enough: Towards Identifiability in Linear Stochastic Dynamics from Steady State

    Sep 17, 2026Saber SalehkaleybarParameter EstimationStochastic Differential Equations

    Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands

  8. PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise

    Sep 8, 2026Mihaly Petreczky, Mohamad Al Ahdab, John LethPAC-Bayesian Generalization BoundsStochastic Linear Dynamical Systems

    CRIStAL, Centrale Lille, Universit´e de Lille, France · Department of Electronic Systems, Aalborg University, Denmark

  9. On the Structural Limits of Machine Learning Decision Systems: An Information-Theoretic, Interaction-Based, and Stochastic-Dynamical Perspective

    Aug 13, 2026Nestor R. Barraza, Gabriel PenaStochastic Linear Dynamical SystemsStatistical Learning Theory

    Universidad Nacional de Tres de Febrero. Departamento de Ciencia y Tecnología. · Universidad de Buenos Aires. Facultad de Ingeniería.

  10. Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks

    Jul 30, 2026Mostafa Haghir ChehreghaniGraph Neural NetworksStochastic Linear Dynamical Systems

    Department of Computer Engineering Amirkabir University of Technology (Tehran Polytechnic) Tehran, Iran

  11. Finite-Sample Closed-Loop Stability of Model Predictive Path Integral Control for Linear Time-Invariant Systems

    Jul 4, 2026Hyung-Jin Yoon, Hunmin KimDynamical SystemsStochastic Linear Dynamical Systems

    Department of Mechanical and Nuclear Engineering, Tennessee Technological University, Cookeville, TN, USA

  12. Deep Spectral Learning of Embedded Latent Transfer Operators for Stochastic Dynamical Systems

    Jun 12, 2026Ryogo Tanaka, Yoshinobu KawaharaDynamical SystemsStochastic Linear Dynamical Systems

    Graduate School of Information Science and Technology, The University of Osaka, Osaka, Japan · Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan

  13. First-Order Trajectory Matching: Fast Ensemble Predictions of Chaotic, Turbulent, Stochastic Systems

    Jun 9, 2026Shreya Jha, Timo Schorlepp, Nicholas Geissler +2Dynamical SystemsSurrogate Modeling

    Courant Institute of Mathematical Sciences, New York University

  14. Stochastic Lifting for Generating Trajectories of Stochastic Physical Systems

    May 28, 2026Jules Berman, Tobias Blickhan, Benjamin PeherstorferDynamical SystemsStochastic Linear Dynamical Systems

    Courant Institute of Mathematical Sciences, New York University, New York, NY 10012, USA.

  15. Sample Complexity of Policy Gradient for Log-Growth Control

    May 26, 2026Qiuhua Pan, Yukai Shen, Liwei Zhang +2Stochastic Linear Dynamical SystemsStochastic Optimal Control

    State Key Laboratory of Submarine Geoscience, School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China · Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai 200240, China · Shanghai Key Laboratory of Perception and Control in Industrial Network Systems, Shanghai 200240, China +1

  16. Rate-Optimal Regret for the Safe Learning-based Control of the Constrained Linear Quadratic Regulator

    Apr 24, 2026Spencer Hutchinson, Nanfei Jiang, Mahnoosh AlizadehStochastic Linear Dynamical SystemsStochastic Optimal Control

    Department of Electrical and Computer Engineering, University of California Santa Barbara

  17. CLT-Optimal Parameter Error Bounds for Linear System Identification

    Apr 23, 2026Yichen Zhou, Stephen TuDynamical SystemsParameter Estimation

    Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, California, USA.

  18. Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series

    Apr 6, 2026Annita Vapsi, Penghang Liu, Saheed Obitayo +8Synthetic Data GenerationTime Series Generation

    JPMorganChase

  19. Exact and Approximate Convex Reformulation of Linear Stochastic Optimal Control with Chance Constraints

    Mar 19, 2026Tanmay Dokania, Yashwanth Kumar NakkaStochastic Optimal ControlChance-Constrained Optimization

    Authors are with the Daniel Guggenheim School of Aerospace Engineering at the Georgia Institute of Technology, Atlanta, GA, 30332 USA.

  20. Symmetric Linear Dynamical Systems are Learnable from Few Observations

    Dec 5, 2025Minh Vu, Andrey Y. Lokhov, Marc VuffrayDynamical SystemsParameter Estimation

    Theoretical Division, Los Alamos National Laboratory, Los Alamos, NM 87545, USA