Learning non-equilibrium diffusions with Schrödinger bridges: from exactly solvable to simulation-free

• URL: http://arxiv.org/abs/2505.16644v1
• Date: Thu, 22 May 2025 13:17:30 GMT
• Title: Learning non-equilibrium diffusions with Schrödinger bridges: from exactly solvable to simulation-free
• Authors: Stephen Y. Zhang, Michael P H Stumpf,
• Abstract summary: We consider the Schr"odinger bridge problem given ensemble measurements of the initial and final configurations of a dynamical system.<n>We propose mvOU-OTFM, a simulation-free algorithm based on flow and score matching for learning the Schr"odinger bridge.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider the Schr\"odinger bridge problem which, given ensemble measurements of the initial and final configurations of a stochastic dynamical system and some prior knowledge on the dynamics, aims to reconstruct the "most likely" evolution of the system compatible with the data. Most existing literature assume Brownian reference dynamics and are implicitly limited to potential-driven dynamics. We depart from this regime and consider reference processes described by a multivariate Ornstein-Uhlenbeck process with generic drift matrix $\mathbf{A} \in \mathbb{R}^{d \times d}$. When $\mathbf{A}$ is asymmetric, this corresponds to a non-equilibrium system with non-conservative forces at play: this is important for applications to biological systems, which are naturally exist out-of-equilibrium. In the case of Gaussian marginals, we derive explicit expressions that characterise the solution of both the static and dynamic Schr\"odinger bridge. For general marginals, we propose mvOU-OTFM, a simulation-free algorithm based on flow and score matching for learning the Schr\"odinger bridge. In application to a range of problems based on synthetic and real single cell data, we demonstrate that mvOU-OTFM achieves higher accuracy compared to competing methods, whilst being significantly faster to train.

Related papers

• Quantum simulation of a noisy classical nonlinear dynamics [2.6874004806796528]
  We consider the problem of simulating dynamics of classical nonlinear dissipative systems with $Ngg 1$ of freedom.<n>To make the problem tractable for quantum computers, we add a weak Gaussian noise to the equation of motion and the initial state.<n>For any constant nonzero noise rate, the runtime quantum scales to $log(N)$, evolution time, inverse error tolerance, and the relative strength of nonlinearity and dissipation.
  arXiv  Detail & Related papers  (2025-07-08T17:25:40Z)
• Lindbladian reverse engineering for general non-equilibrium steady states: A scalable null-space approach [49.1574468325115]
  We introduce a method for reconstructing the corresponding Lindbaldian master equation given any target NESS. The kernel (null-space) of the correlation matrix corresponds to Lindbladian solutions. We illustrate the method in different systems, ranging from bosonic Gaussian to dissipative-driven collective spins.
  arXiv  Detail & Related papers  (2024-08-09T19:00:18Z)
• Schrödinger Bridge with Quadratic State Cost is Exactly Solvable [3.820235868126608]
  We propose a regularized variant of the Schr"odinger bridge with a quadratic state cost-to-go that incentivizes the optimal sample paths to stay close to a nominal level. Unlike the conventional Schr"odinger bridge, the regularization induces a state-dependent rate of killing and creation of probability mass. We derive this Markov kernel in closed form, blackshowing that the regularized Schr"odinger bridge is exactly solvable, even for non-Gaussian endpoints.
  arXiv  Detail & Related papers  (2024-06-01T17:22:00Z)
• On the Contraction Coefficient of the Schr\"odinger Bridge for Stochastic Linear Systems [15.022863946000495]
  A popular method to numerically solve the Schr"odinger bridge problems is via contractive fixed point recursions. We study a priori estimates for the contraction coefficients associated with the convergence of respective Schr"odinger systems.
  arXiv  Detail & Related papers  (2023-09-12T22:24:05Z)
• Simulation-free Schr\"odinger bridges via score and flow matching [89.4231207928885]
  We present simulation-free score and flow matching ([SF]$2$M) Our method generalizes both the score-matching loss used in the training of diffusion models and the recently proposed flow matching loss used in the training of continuous flows. Notably, [SF]$2$M is the first method to accurately model cell dynamics in high dimensions and can recover known gene regulatory networks simulated data.
  arXiv  Detail & Related papers  (2023-07-07T15:42:35Z)
• Machine learning of hidden variables in multiscale fluid simulation [77.34726150561087]
  Solving fluid dynamics equations often requires the use of closure relations that account for missing microphysics. In our study, a partial differential equation simulator that is end-to-end differentiable is used to train judiciously placed neural networks. We show that this method enables an equation based approach to reproduce non-linear, large Knudsen number plasma physics.
  arXiv  Detail & Related papers  (2023-06-19T06:02:53Z)
• Vectorization of the density matrix and quantum simulation of the von Neumann equation of time-dependent Hamiltonians [65.268245109828]
  We develop a general framework to linearize the von-Neumann equation rendering it in a suitable form for quantum simulations. We show that one of these linearizations of the von-Neumann equation corresponds to the standard case in which the state vector becomes the column stacked elements of the density matrix. A quantum algorithm to simulate the dynamics of the density matrix is proposed.
  arXiv  Detail & Related papers  (2023-06-14T23:08:51Z)
• The Schr\"odinger Bridge between Gaussian Measures has a Closed Form [101.79851806388699]
  We focus on the dynamic formulation of OT, also known as the Schr"odinger bridge (SB) problem. In this paper, we provide closed-form expressions for SBs between Gaussian measures.
  arXiv  Detail & Related papers  (2022-02-11T15:59:01Z)
• Inverting brain grey matter models with likelihood-free inference: a tool for trustable cytoarchitecture measurements [62.997667081978825]
  characterisation of the brain grey matter cytoarchitecture with quantitative sensitivity to soma density and volume remains an unsolved challenge in dMRI. We propose a new forward model, specifically a new system of equations, requiring a few relatively sparse b-shells. We then apply modern tools from Bayesian analysis known as likelihood-free inference (LFI) to invert our proposed model.
  arXiv  Detail & Related papers  (2021-11-15T09:08:27Z)
• Uncertainty quantification in a mechanical submodel driven by a Wasserstein-GAN [0.0]
  We show that the use of non-linear techniques in machine learning and data-driven methods is highly relevant. Generative Adversarial Networks (GANs) are suited for such applications, where the Wasserstein-GAN with gradient penalty variant offers improved results.
  arXiv  Detail & Related papers  (2021-10-26T13:18:06Z)

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.