A deep learning functional estimator of optimal dynamics for sampling large deviations

Oakes, Tom H E and Moss, Adam and Garrahan, Juan P (2020) A deep learning functional estimator of optimal dynamics for sampling large deviations. Machine Learning: Science and Technology, 1 (3). 035004. ISSN 2632-2153

[thumbnail of Oakes_2020_Mach._Learn.__Sci._Technol._1_035004.pdf] Text
Oakes_2020_Mach._Learn.__Sci._Technol._1_035004.pdf - Published Version

Download (1MB)


In stochastic systems, numerically sampling the relevant trajectories for the estimation of the large deviation statistics of time-extensive observables requires overcoming their exponential (in space and time) scarcity. The optimal way to access these rare events is by means of an auxiliary dynamics obtained from the original one through the so-called 'generalised Doob transformation'. While this optimal dynamics is guaranteed to exist its use is often impractical, as to define it requires the often impossible task of diagonalising a (tilted) dynamical generator. While approximate schemes have been devised to overcome this issue they are difficult to automate as they tend to require knowledge of the systems under study. Here we address this problem from the perspective of deep learning. We devise an iterative semi-supervised learning scheme which converges to the optimal or Doob dynamics with the clear advantage of requiring no prior knowledge of the system. We test our method in a paradigmatic statistical mechanics model with non-trivial dynamical fluctuations, the fully packed classical dimer model on the square lattice, showing that it compares favourably with more traditional approaches. We discuss broader implications of our results for the study of rare dynamical trajectories.

Item Type: Article
Subjects: STM Library > Multidisciplinary
Depositing User: Managing Editor
Date Deposited: 05 Jul 2023 04:00
Last Modified: 12 Oct 2023 05:59
URI: http://open.journal4submit.com/id/eprint/2428

Actions (login required)

View Item
View Item