Generative optimal transport via forward-backward HJB matching

• URL: http://arxiv.org/abs/2604.07762v1
• Date: Thu, 09 Apr 2026 03:31:25 GMT
• Title: Generative optimal transport via forward-backward HJB matching
• Abstract summary: Controlling the evolution of a many-body system from a disordered reference state to a structured target ensemble, arises naturally in non-equilibrium statistical mechanics and control.<n>We present a framework that provides a physically interpretable description of transport in terms of path-space free energy, risk-sensitive control, and spatial cost geometry.<n>Our results establish a unifying connection between optimal control, Schrdinger bridge theory, and non-equilibrium statistical mechanics.
• Score: 0.23332469289621782
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Controlling the evolution of a many-body stochastic system from a disordered reference state to a structured target ensemble, characterized empirically through samples, arises naturally in non-equilibrium statistical mechanics and stochastic control. The natural relaxation of such a system - driven by diffusion - runs from the structured target toward the disordered reference. The natural question is then: what is the minimum-work stochastic process that reverses this relaxation, given a pathwise cost functional combining spatial penalties and control effort? Computing this optimal process requires knowledge of trajectories that already sample the target ensemble - precisely the object one is trying to construct. We resolve this by establishing a time-reversal duality: the value function governing the hard backward dynamics satisfies an equivalent forward-in-time HJB equation, whose solution can be read off directly from the tractable forward relaxation trajectories. Via the Cole-Hopf transformation and its associated Feynman-Kac representation, this forward potential is computed as a path-space free energy averaged over these forward trajectories - the same relaxation paths that are easy to simulate - without any backward simulation or knowledge of the target beyond samples. The resulting framework provides a physically interpretable description of stochastic transport in terms of path-space free energy, risk-sensitive control, and spatial cost geometry. We illustrate the theory with numerical examples that visualize the learned value function and the induced controlled diffusions, demonstrating how spatial cost fields shape transport geometry analogously to Fermat's Principle in inhomogeneous media. Our results establish a unifying connection between stochastic optimal control, Schrödinger bridge theory, and non-equilibrium statistical mechanics.

Related papers

• Schrödinger Bridges over Kinetic Swarming Models [16.998652690384596]
  We consider finite-horizon minimum-energy collective steering for swarms subject to disturbances.<n>Our objective is to steer the swarm between prescribed endpoint distributions using a state-feedback control.<n>We derive necessary optimality systems with a time-symmetric structure reminiscent of classical Schrdinger bridges.
  arXiv  Detail & Related papers  (2026-08-26T01:34:36Z)
• Free energy Estimation on Any State Space [49.560935787029564]
  Recent work learns neural transports to significantly accelerate the efficiency in the finite-time regime.<n>In this paper, we generalize this framework to arbitrary state spaces.<n> Experiments validate the effectiveness and efficiency of the proposed method.
  arXiv  Detail & Related papers  (2026-05-29T09:34:53Z)
• Lagrangian Flow Matching: A Least-Action Framework for Principled Path Design [14.77320535984857]
  Flow matching trains a neural velocity field by regression against a target velocity associated with a prescribed probability path.<n>We propose Lagrangian flow matching, a physics-based framework in which the probability path and velocity field are determined by minimizing the action of a general Lagrangian.
  arXiv  Detail & Related papers  (2026-05-14T21:05:03Z)
• Rare Event Analysis via Stochastic Optimal Control [39.211234628277744]
  We introduce a framework that casts committor estimation as an optimal control (SOC) problem.<n>We develop two complementary objectives: a direct backpropagation loss and a principled off-policy Value Matching loss.<n>On benchmark systems, the framework yields more accurate committor estimates, reaction rates, and equilibrium constants than existing methods.
  arXiv  Detail & Related papers  (2026-04-14T18:34:38Z)
• Forward and inverse problems for measure flows in Bayes Hilbert spaces [10.897369732123844]
  We study forward and inverse problems for time-dependent probability measures in Bayes--Hilbert spaces.<n>We prove existence of minimizers, derive first-variation formulas, establish local stability of the observation map, and deduce recovery of the evolving law.
  arXiv  Detail & Related papers  (2026-03-20T04:01:41Z)
• Differentiable Stochastic Traffic Dynamics: Physics-Informed Generative Modelling in Transportation [0.0]
  This work develops a framework in which the physics constraint itself is distributional and spatial, derived from traffic-flow dynamics.<n>The framework provides a basis for distributional traffic-state estimation and for fundamental analysis in a physics-informed generative setting.
  arXiv  Detail & Related papers  (2026-03-10T04:25:20Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• Minimum-Excess-Work Guidance [17.15668604906196]
  We propose a regularization framework for guiding pre-trained probability flow generative models.<n>Our approach enables efficient guidance in sparse-data regimes common to scientific applications.<n>We demonstrate the framework's versatility on a coarse-grained protein model.
  arXiv  Detail & Related papers  (2025-05-19T17:19:43Z)
• FEAT: Free energy Estimators with Adaptive Transport [56.65918359070768]
  We present Free energy Estimators with Adaptive Transport (FEAT), a novel framework for free energy estimation.<n>FEAT provides consistent, minimum-variance estimators based on escorted Jarzynski equality and controlled Crooks theorem.<n> Experimental validation on toy examples, molecular simulations, and quantum field theory demonstrates improvements over existing learning-based methods.
  arXiv  Detail & Related papers  (2025-04-15T15:16:18Z)
• Generalized Flow Matching for Transition Dynamics Modeling [14.76793118877456]
  We propose a data-driven approach to warm-up the simulation by learning nonlinearities from local dynamics. Specifically, we infer a potential energy function from local dynamics data to find plausible paths between two metastable states. We validate the effectiveness of the proposed method to sample probable paths on both synthetic and real-world molecular systems.
  arXiv  Detail & Related papers  (2024-10-19T15:03:39Z)
• Dynamical Measure Transport and Neural PDE Solvers for Sampling [77.38204731939273]
  We tackle the task of sampling from a probability density as transporting a tractable density function to the target. We employ physics-informed neural networks (PINNs) to approximate the respective partial differential equations (PDEs) solutions. PINNs allow for simulation- and discretization-free optimization and can be trained very efficiently.
  arXiv  Detail & Related papers  (2024-07-10T17:39:50Z)
• Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion [88.45326906116165]
  We present a new framework to formulate the trajectory prediction task as a reverse process of motion indeterminacy diffusion (MID) We encode the history behavior information and the social interactions as a state embedding and devise a Transformer-based diffusion model to capture the temporal dependencies of trajectories. Experiments on the human trajectory prediction benchmarks including the Stanford Drone and ETH/UCY datasets demonstrate the superiority of our method.
  arXiv  Detail & Related papers  (2022-03-25T16:59:08Z)
• Probing eigenstate thermalization in quantum simulators via fluctuation-dissipation relations [77.34726150561087]
  The eigenstate thermalization hypothesis (ETH) offers a universal mechanism for the approach to equilibrium of closed quantum many-body systems. Here, we propose a theory-independent route to probe the full ETH in quantum simulators by observing the emergence of fluctuation-dissipation relations. Our work presents a theory-independent way to characterize thermalization in quantum simulators and paves the way to quantum simulate condensed matter pump-probe experiments.
  arXiv  Detail & Related papers  (2020-07-20T18:00:02Z)

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.