IDEAS home Printed from https://ideas.repec.org/a/eee/spapps/v190y2025ics0304414925002078.html

Essential barrier height and a probabilistic approach in characterizing potential landscape

Author

Listed:
  • Li, Yao
  • Tao, Molei
  • Wang, Shirou

Abstract

This paper proposes a probabilistic approach to investigate the shape of landscapes of multi-dimensional potential functions. Under a suitable coupling scheme, two copies of the overdamped Langevin dynamics associated with the potential function are coupled, and the coupling times are collected. Assuming a set of intuitive yet technically challenging conditions on the coupling scheme, it is shown that the tail distributions of the coupling times exhibit qualitatively different dependencies on the noise magnitude for single-well versus multi-well potential functions. More specifically, for convex single-well potentials, the negative tail exponent of the coupling time distribution is uniformly bounded away from zero by the convexity parameter and is independent of the noise magnitude. In contrast, for multi-well potentials, the negative tail exponent decreases exponentially as the noise vanishes, with the decay rate governed by the essential barrier height, a quantity introduced in this paper to characterize the non-convex nature of the potential function. Numerical investigations are conducted for a variety of examples, including the Rosenbrock function, interacting particle systems, and loss functions arising in artificial neural networks. These examples not only illustrate the theoretical results in various contexts but also provide crucial numerical validation of the conjectured assumptions, which are essential to the theoretical analysis yet lie beyond the reach of standard technical tools.

Suggested Citation

  • Li, Yao & Tao, Molei & Wang, Shirou, 2025. "Essential barrier height and a probabilistic approach in characterizing potential landscape," Stochastic Processes and their Applications, Elsevier, vol. 190(C).
    • Handle: RePEc:eee:spapps:v:190:y:2025:i:c:s0304414925002078
    DOI: 10.1016/j.spa.2025.104763
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0304414925002078
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.spa.2025.104763?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Alexander Lipton & Vadim Kaushansky, 2018. "On the First Hitting Time Density of an Ornstein-Uhlenbeck Process," Papers 1810.02390, arXiv.org, revised Oct 2018.
    2. Gobet, Emmanuel & Menozzi, Stéphane, 2004. "Exact approximation rate of killed hypoelliptic diffusions using the discrete Euler scheme," Stochastic Processes and their Applications, Elsevier, vol. 112(2), pages 201-223, August.
    3. Gobet, Emmanuel & Menozzi, Stéphane, 2010. "Stopped diffusion processes: Boundary corrections and overshoot," Stochastic Processes and their Applications, Elsevier, vol. 120(2), pages 130-162, February.
    4. Nummelin, Esa & Tuominen, Pekka, 1982. "Geometric ergodicity of Harris recurrent Marcov chains with applications to renewal theory," Stochastic Processes and their Applications, Elsevier, vol. 12(2), pages 187-202, March.
    5. Sirignano, Justin & Spiliopoulos, Konstantinos, 2020. "Mean field analysis of neural networks: A central limit theorem," Stochastic Processes and their Applications, Elsevier, vol. 130(3), pages 1820-1852.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Liang, V. & Borovkov, K., 2025. "On time-dependent boundary crossing probabilities of diffusion processes as differentiable functionals of the boundary," Stochastic Processes and their Applications, Elsevier, vol. 190(C).
    2. Sebastian Jaimungal, 2022. "Reinforcement learning and stochastic optimisation," Finance and Stochastics, Springer, vol. 26(1), pages 103-129, January.
    3. Alexander Lipton, 2020. "Old Problems, Classical Methods, New Solutions," Papers 2003.06903, arXiv.org.
    4. Florian Bourgey & Emmanuel Gobet & Ying Jiao, 2024. "Bridging socioeconomic pathways of $$\textrm{CO}_2$$ CO 2 emission and credit risk," Annals of Operations Research, Springer, vol. 336(1), pages 1197-1218, May.
    5. Rey, Clément, 2019. "Approximation of Markov semigroups in total variation distance under an irregular setting: An application to the CIR process," Stochastic Processes and their Applications, Elsevier, vol. 129(2), pages 539-571.
    6. Bianchi, Pascal & Hachem, Walid & Priser, Victor, 2025. "Long run convergence of discrete-time interacting particle systems of the McKean–Vlasov type," Stochastic Processes and their Applications, Elsevier, vol. 186(C).
    7. Matoussi Anis & Sabbagh Wissal, 2016. "Numerical computation for backward doubly SDEs with random terminal time," Monte Carlo Methods and Applications, De Gruyter, vol. 22(3), pages 229-258, September.
    8. Alexander Lipton & Marcos Lopez de Prado, 2020. "A closed-form solution for optimal mean-reverting trading strategies," Papers 2003.10502, arXiv.org.
    9. Christian Meier & Lingfei Li & Gongqiu Zhang, 2021. "Simulation of Multidimensional Diffusions with Sticky Boundaries via Markov Chain Approximation," Papers 2107.04260, arXiv.org.
    10. Ruixiang Zhang & Ziyu Zhu & Meng Yuan & Yihan Guo & Jie Song & Xuanxuan Shi & Yu Wang & Yaojie Sun, 2023. "Regional Residential Short-Term Load-Interval Forecasting Based on SSA-LSTM and Load Consumption Consistency Analysis," Energies, MDPI, vol. 16(24), pages 1-17, December.
    11. Andrey Itkin & Dmitry Muravey, 2020. "Semi-analytic pricing of double barrier options with time-dependent barriers and rebates at hit," Papers 2009.09342, arXiv.org, revised Oct 2020.
    12. Remigijus Mikulevičius & Changyong Zhang, 2024. "Convergence of Weak Euler Approximation for Nondegenerate Stochastic Differential Equations Driven by Point and Martingale Measures," Journal of Theoretical Probability, Springer, vol. 37(1), pages 43-80, March.
    13. Konstantin Avrachenkov & Alexey Piunovskiy & Yi Zhang, 2018. "Hitting Times in Markov Chains with Restart and their Application to Network Centrality," Methodology and Computing in Applied Probability, Springer, vol. 20(4), pages 1173-1188, December.
    14. Pagès Gilles, 2007. "Multi-step Richardson-Romberg Extrapolation: Remarks on Variance Control and Complexity," Monte Carlo Methods and Applications, De Gruyter, vol. 13(1), pages 37-70, April.
    15. Richard C. Bradley, 2021. "On some basic features of strictly stationary, reversible Markov chains," Journal of Time Series Analysis, Wiley Blackwell, vol. 42(5-6), pages 499-533, September.
    16. Herrmann, Samuel & Massin, Nicolas, 2023. "Exact simulation of the first passage time through a given level of jump diffusions," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 203(C), pages 553-576.
    17. David Gamarnik & Eren C. Kızıldağ & Ilias Zadik, 2025. "Stationary Points of a Shallow Neural Network with Quadratic Activations and the Global Optimality of the Gradient Descent Algorithm," Mathematics of Operations Research, INFORMS, vol. 50(1), pages 209-251, February.
    18. Sewoong Oh & Soumik Pal & Raghav Somani & Raghavendra Tripathi, 2024. "Gradient Flows on Graphons: Existence, Convergence, Continuity Equations," Journal of Theoretical Probability, Springer, vol. 37(2), pages 1469-1522, June.
    19. Allam, Abdelazziz & Mourid, Tahar, 2002. "Geometric absolute regularity of Banach space-valued autoregressive processes," Statistics & Probability Letters, Elsevier, vol. 60(3), pages 241-252, December.
    20. Eunji Lim & Peter W. Glynn, 2023. "Simulation-Based Prediction," Operations Research, INFORMS, vol. 71(1), pages 47-60, January.

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:spapps:v:190:y:2025:i:c:s0304414925002078. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/505572/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.