Time-Reversible Bridges of Data with Machine Learning

• URL: http://arxiv.org/abs/2412.13665v1
• Date: Wed, 18 Dec 2024 09:47:19 GMT
• Title: Time-Reversible Bridges of Data with Machine Learning
• Authors: Ludwig Winkler,
• Abstract summary: This thesis presents novel approaches to learn time-reversible deterministic and dynamics constrained by initial and final conditions. The dynamics are inferred by machine learning algorithms from observed data.
• Score: 0.0
• License:
• Abstract: The analysis of dynamical systems is a fundamental tool in the natural sciences and engineering. It is used to understand the evolution of systems as large as entire galaxies and as small as individual molecules. With predefined conditions on the evolution of dy-namical systems, the underlying differential equations have to fulfill specific constraints in time and space. This class of problems is known as boundary value problems. This thesis presents novel approaches to learn time-reversible deterministic and stochastic dynamics constrained by initial and final conditions. The dynamics are inferred by machine learning algorithms from observed data, which is in contrast to the traditional approach of solving differential equations by numerical integration. The work in this thesis examines a set of problems of increasing difficulty each of which is concerned with learning a different aspect of the dynamics. Initially, we consider learning deterministic dynamics from ground truth solutions which are constrained by deterministic boundary conditions. Secondly, we study a boundary value problem in discrete state spaces, where the forward dynamics follow a stochastic jump process and the boundary conditions are discrete probability distributions. In particular, the stochastic dynamics of a specific jump process, the Ehrenfest process, is considered and the reverse time dynamics are inferred with machine learning. Finally, we investigate the problem of inferring the dynamics of a continuous-time stochastic process between two probability distributions without any reference information. Here, we propose a novel criterion to learn time-reversible dynamics of two stochastic processes to solve the Schr\"odinger Bridge Problem.

Related papers

• Learning Controlled Stochastic Differential Equations [61.82896036131116]
  This work proposes a novel method for estimating both drift and diffusion coefficients of continuous, multidimensional, nonlinear controlled differential equations with non-uniform diffusion. We provide strong theoretical guarantees, including finite-sample bounds for (L2), (Linfty), and risk metrics, with learning rates adaptive to coefficients' regularity. Our method is available as an open-source Python library.
  arXiv  Detail & Related papers  (2024-11-04T11:09:58Z)
• A Dynamical View of the Question of Why [10.243488468625783]
  We present two key lemmas to compute causal contributions and frame them as reinforcement learning problems. Our approach offers formal and computational tools for uncovering and quantifying causal relationships in diffusion processes. In fairly intricate experiments and through sheer learning, our framework reveals and quantifies causal links, which otherwise seem inexplicable.
  arXiv  Detail & Related papers  (2024-02-14T18:44:05Z)
• Individualized Dosing Dynamics via Neural Eigen Decomposition [51.62933814971523]
  We introduce the Neural Eigen Differential Equation algorithm (NESDE) NESDE provides individualized modeling, tunable generalization to new treatment policies, and fast, continuous, closed-form prediction. We demonstrate the robustness of NESDE in both synthetic and real medical problems, and use the learned dynamics to publish simulated medical gym environments.
  arXiv  Detail & Related papers  (2023-06-24T17:01:51Z)
• An information field theory approach to Bayesian state and parameter estimation in dynamical systems [0.0]
  This paper develops a scalable Bayesian approach to state and parameter estimation suitable for continuous-time, deterministic dynamical systems. We construct a physics-informed prior probability measure on the function space of system responses so that functions that satisfy the physics are more likely.
  arXiv  Detail & Related papers  (2023-06-03T16:36:43Z)
• Automatically identifying ordinary differential equations from data [0.0]
  We propose a methodology to identify dynamical laws by integrating denoising techniques to smooth the signal. We evaluate our method on well-known ordinary differential equations with an ensemble of random initial conditions.
  arXiv  Detail & Related papers  (2023-04-21T18:00:03Z)
• Semi-supervised Learning of Partial Differential Operators and Dynamical Flows [68.77595310155365]
  We present a novel method that combines a hyper-network solver with a Fourier Neural Operator architecture. We test our method on various time evolution PDEs, including nonlinear fluid flows in one, two, and three spatial dimensions. The results show that the new method improves the learning accuracy at the time point of supervision point, and is able to interpolate and the solutions to any intermediate time.
  arXiv  Detail & Related papers  (2022-07-28T19:59:14Z)
• Discovering stochastic dynamical equations from biological time series data [0.0]
  We present an equation discovery that takes time series data of variables as input and outputs a differential state equation. We show that we can recover the correct equations, and thus infer the structure of their stability, accurately from the analysis of time series data alone. We demonstrate our method on two realworld datasets -- fish schooling and single-cell migration.
  arXiv  Detail & Related papers  (2022-05-05T13:44:24Z)
• Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations [62.81701992551728]
  We present a physics-informed framework for solving time-dependent partial differential equations. Our model utilizes discrete cosine transforms to encode spatial and recurrent neural networks. We show experimental results on the Taylor-Green vortex solution to the Navier-Stokes equations.
  arXiv  Detail & Related papers  (2022-02-24T20:46:52Z)
• Structure-Preserving Learning Using Gaussian Processes and Variational Integrators [62.31425348954686]
  We propose the combination of a variational integrator for the nominal dynamics of a mechanical system and learning residual dynamics with Gaussian process regression. We extend our approach to systems with known kinematic constraints and provide formal bounds on the prediction uncertainty.
  arXiv  Detail & Related papers  (2021-12-10T11:09:29Z)
• Consistency of mechanistic causal discovery in continuous-time using Neural ODEs [85.7910042199734]
  We consider causal discovery in continuous-time for the study of dynamical systems. We propose a causal discovery algorithm based on penalized Neural ODEs.
  arXiv  Detail & Related papers  (2021-05-06T08:48:02Z)
• An exact kernel framework for spatio-temporal dynamics [0.04297070083645048]
  A kernel-based framework for system dynamics analysis is introduced. It applies to situations when the underlying system dynamics are governed by a dynamic equation.
  arXiv  Detail & Related papers  (2020-11-13T10:32:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.