Minimum-Excess-Work Guidance

• URL: http://arxiv.org/abs/2505.13375v3
• Date: Fri, 23 May 2025 05:18:25 GMT
• Title: Minimum-Excess-Work Guidance
• Authors: Christopher Kolloff, Tobias Höppe, Emmanouil Angelis, Mathias Jacob Schreiner, Stefan Bauer, Andrea Dittadi, Simon Olsson,
• Abstract summary: 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.
• Score: 17.15668604906196
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a regularization framework inspired by thermodynamic work for guiding pre-trained probability flow generative models (e.g., continuous normalizing flows or diffusion models) by minimizing excess work, a concept rooted in statistical mechanics and with strong conceptual connections to optimal transport. Our approach enables efficient guidance in sparse-data regimes common to scientific applications, where only limited target samples or partial density constraints are available. We introduce two strategies: Path Guidance for sampling rare transition states by concentrating probability mass on user-defined subsets, and Observable Guidance for aligning generated distributions with experimental observables while preserving entropy. We demonstrate the framework's versatility on a coarse-grained protein model, guiding it to sample transition configurations between folded/unfolded states and correct systematic biases using experimental data. The method bridges thermodynamic principles with modern generative architectures, offering a principled, efficient, and physics-inspired alternative to standard fine-tuning in data-scarce domains. Empirical results highlight improved sample efficiency and bias reduction, underscoring its applicability to molecular simulations and beyond.

Related papers

• Navigating Sparse Molecular Data with Stein Diffusion Guidance [48.21071466968102]
  optimal control (SOC) has emerged as a principled framework for fine-tuning diffusion models.<n>A class of training-free approaches has been developed that guides diffusion models using off-the-shelf classifiers on predicted clean samples.<n>We propose a novel training-free guidance framework based on a surrogate optimal control objective.
  arXiv  Detail & Related papers  (2025-07-07T21:14:27Z)
• Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design [53.93023688824764]
  We address the problem of fine-tuning diffusion models for reward-guided generation in biomolecular design.<n>We propose an iterative distillation-based fine-tuning framework that enables diffusion models to optimize for arbitrary reward functions.<n>Our off-policy formulation, combined with KL divergence minimization, enhances training stability and sample efficiency compared to existing RL-based methods.
  arXiv  Detail & Related papers  (2025-07-01T05:55:28Z)
• Self-Refining Training for Amortized Density Functional Theory [5.5541132320126945]
  We propose a novel method that reduces the dependency of amortized DFT solvers on large pre-collected datasets by introducing a self-refining training strategy.<n>We derive our method as a minimization of the variational upper bound on the KL-divergence measuring the discrepancy between the generated samples and the target Boltzmann distribution defined by the ground state energy.
  arXiv  Detail & Related papers  (2025-06-02T00:32:32Z)
• Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching [33.9461078261722]
  We introduce Adjoint Sampling, a highly scalable and efficient algorithm for learning diffusion processes that sample from unnormalized densities.<n>We show how to incorporate key symmetries, as well as periodic boundary conditions, for modeling molecules in both cartesian and torsional coordinates.<n>We demonstrate the effectiveness of our approach through extensive experiments on classical energy functions, and further scale up to neural network-based energy models.
  arXiv  Detail & Related papers  (2025-04-16T02:20:06Z)
• Conditional Lagrangian Wasserstein Flow for Time Series Imputation [3.583527519172841]
  Conditional Lagrangian Wasserstein Flow is a novel method for time series imputation.<n>We learn the velocity by minimizing the corresponding kinetic energy.<n>To enhance the model's performance, we estimate the gradient of a task-specific potential function.
  arXiv  Detail & Related papers  (2024-10-10T02:46:28Z)
• 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)
• On the Trajectory Regularity of ODE-based Diffusion Sampling [79.17334230868693]
  Diffusion-based generative models use differential equations to establish a smooth connection between a complex data distribution and a tractable prior distribution. In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models.
  arXiv  Detail & Related papers  (2024-05-18T15:59:41Z)
• Physics-Informed Diffusion Models [0.0]
  We present a framework that unifies generative modeling and partial differential equation fulfillment.<n>Our approach reduces the residual error by up to two orders of magnitude compared to previous work in a fluid flow case study.
  arXiv  Detail & Related papers  (2024-03-21T13:52:55Z)
• Space-Time Diffusion Bridge [0.4527270266697462]
  We introduce a novel method for generating new synthetic samples independent and identically distributed from real probability distributions. We use space-time mixing strategies that extend across temporal and spatial dimensions. We validate the efficacy of our space-time diffusion approach with numerical experiments.
  arXiv  Detail & Related papers  (2024-02-13T23:26:11Z)
• Constrained Synthesis with Projected Diffusion Models [47.56192362295252]
  This paper introduces an approach to generative diffusion processes the ability to satisfy and certify compliance with constraints and physical principles. The proposed method recast the traditional process of generative diffusion as a constrained distribution problem to ensure adherence to constraints.
  arXiv  Detail & Related papers  (2024-02-05T22:18:16Z)
• Distributed Markov Chain Monte Carlo Sampling based on the Alternating Direction Method of Multipliers [143.6249073384419]
  In this paper, we propose a distributed sampling scheme based on the alternating direction method of multipliers. We provide both theoretical guarantees of our algorithm's convergence and experimental evidence of its superiority to the state-of-the-art. In simulation, we deploy our algorithm on linear and logistic regression tasks and illustrate its fast convergence compared to existing gradient-based methods.
  arXiv  Detail & Related papers  (2024-01-29T02:08:40Z)
• Sampling with Mollified Interaction Energy Descent [57.00583139477843]
  We present a new optimization-based method for sampling called mollified interaction energy descent (MIED) MIED minimizes a new class of energies on probability measures called mollified interaction energies (MIEs) We show experimentally that for unconstrained sampling problems our algorithm performs on par with existing particle-based algorithms like SVGD.
  arXiv  Detail & Related papers  (2022-10-24T16:54:18Z)
• Comparing Probability Distributions with Conditional Transport [63.11403041984197]
  We propose conditional transport (CT) as a new divergence and approximate it with the amortized CT (ACT) cost. ACT amortizes the computation of its conditional transport plans and comes with unbiased sample gradients that are straightforward to compute. On a wide variety of benchmark datasets generative modeling, substituting the default statistical distance of an existing generative adversarial network with ACT is shown to consistently improve the performance.
  arXiv  Detail & Related papers  (2020-12-28T05:14:22Z)

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.