Learning diffusion at lightspeed

• URL: http://arxiv.org/abs/2406.12616v2
• Date: Fri, 18 Oct 2024 16:09:52 GMT
• Title: Learning diffusion at lightspeed
• Authors: Antonio Terpin, Nicolas Lanzetti, Martin Gadea, Florian Dörfler,
• Abstract summary: Existing models to learn the diffusion terms from observational data rely on complex bilevel optimization problems. We propose a new simple model, JKOnet*, which bypasses the complexity of existing architectures. JKOnet* minimizes a simple quadratic loss and outperforms other baselines in terms of sample efficiency, computational complexity, and accuracy.
• Score: 4.154846138501937
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion regulates numerous natural processes and the dynamics of many successful generative models. Existing models to learn the diffusion terms from observational data rely on complex bilevel optimization problems and model only the drift of the system. We propose a new simple model, JKOnet*, which bypasses the complexity of existing architectures while presenting significantly enhanced representational capabilities: JKOnet* recovers the potential, interaction, and internal energy components of the underlying diffusion process. JKOnet* minimizes a simple quadratic loss and outperforms other baselines in terms of sample efficiency, computational complexity, and accuracy. Additionally, JKOnet* provides a closed-form optimal solution for linearly parametrized functionals, and, when applied to predict the evolution of cellular processes from real-world data, it achieves state-of-the-art accuracy at a fraction of the computational cost of all existing methods. Our methodology is based on the interpretation of diffusion processes as energy-minimizing trajectories in the probability space via the so-called JKO scheme, which we study via its first-order optimality conditions.

Related papers

• Divergence Minimization Preference Optimization for Diffusion Model Alignment [58.651951388346525]
  Divergence Minimization Preference Optimization (DMPO) is a principled method for aligning diffusion models by minimizing reverse KL divergence.<n>Our results show that diffusion models fine-tuned with DMPO can consistently outperform or match existing techniques.<n>DMPO unlocks a robust and elegant pathway for preference alignment, bridging principled theory with practical performance in diffusion models.
  arXiv  Detail & Related papers  (2025-07-10T07:57:30Z)
• 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)
• Simulation-Free Differential Dynamics through Neural Conservation Laws [22.4113724471297]
  We present a novel simulation-free framework for training continuous-time diffusion processes over very general objective functions.<n>We propose a coupled parameterization which jointly models a time-dependent density function, or probability path, and the dynamics of a diffusion process that generates this probability path.
  arXiv  Detail & Related papers  (2025-06-23T13:04:23Z)
• Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme [98.04239223945508]
  Learning population dynamics involves recovering the underlying process that governs particle evolution.<n>Recent methods frame this as an energy problem in probability space and leverage the celebrated JKO scheme for efficient time discretization.
  arXiv  Detail & Related papers  (2025-06-02T10:08:03Z)
• Learning Distributions of Complex Fluid Simulations with Diffusion Graph Networks [23.196852966408482]
  We propose a graph-based latent diffusion model that enables direct sampling of states from their equilibrium distribution. This allows for the efficient geometries of flow statistics without running long and expensive numerical simulations. We apply this method to a range of fluid dynamics tasks, such as predicting pressure on 3D wing models in turbulent flow.
  arXiv  Detail & Related papers  (2025-03-19T13:04:39Z)
• A Data-Driven Framework for Discovering Fractional Differential Equations in Complex Systems [8.206685537936078]
  This study introduces a stepwise data-driven framework for discovering fractional differential equations (FDEs) directly from data. Our framework applies deep neural networks as surrogate models for denoising and reconstructing sparse and noisy observations. We validate the framework across various datasets, including synthetic anomalous diffusion data and experimental data on the creep behavior of frozen soils.
  arXiv  Detail & Related papers  (2024-12-05T08:38:30Z)
• Optimal Transport-Based Displacement Interpolation with Data Augmentation for Reduced Order Modeling of Nonlinear Dynamical Systems [0.0]
  We present a novel reduced-order Model (ROM) that exploits optimal transport theory and displacement to enhance the representation of nonlinear dynamics in complex systems. We show improved accuracy and efficiency in predicting complex system behaviors, indicating the potential of this approach for a wide range of applications in computational physics and engineering.
  arXiv  Detail & Related papers  (2024-11-13T16:29:33Z)
• DiffSG: A Generative Solver for Network Optimization with Diffusion Model [75.27274046562806]
  Diffusion generative models can consider a broader range of solutions and exhibit stronger generalization by learning parameters. We propose a new framework, which leverages intrinsic distribution learning of diffusion generative models to learn high-quality solutions.
  arXiv  Detail & Related papers  (2024-08-13T07:56:21Z)
• Data-Driven Stochastic Closure Modeling via Conditional Diffusion Model and Neural Operator [0.0]
  Closure models are widely used in simulating complex multiscale dynamical systems such as turbulence and the earth system. For systems without a clear scale, generalization deterministic and local closure models often lack enough capability. We propose a datadriven modeling framework for constructing neural operator and non-local closure models.
  arXiv  Detail & Related papers  (2024-08-06T05:21:31Z)
• Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review [63.31328039424469]
  This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. We explain the application of various RL algorithms, including PPO, differentiable optimization, reward-weighted MLE, value-weighted sampling, and path consistency learning.
  arXiv  Detail & Related papers  (2024-07-18T17:35:32Z)
• Momentum Particle Maximum Likelihood [2.4561590439700076]
  We propose an analogous dynamical-systems-inspired approach to minimizing the free energy functional. By discretizing the system, we obtain a practical algorithm for Maximum likelihood estimation in latent variable models. The algorithm outperforms existing particle methods in numerical experiments and compares favourably with other MLE algorithms.
  arXiv  Detail & Related papers  (2023-12-12T14:53:18Z)
• Learning Latent Dynamics via Invariant Decomposition and (Spatio-)Temporal Transformers [0.6767885381740952]
  We propose a method for learning dynamical systems from high-dimensional empirical data. We focus on the setting in which data are available from multiple different instances of a system. We study behaviour through simple theoretical analyses and extensive experiments on synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2023-06-21T07:52:07Z)
• Score-based Diffusion Models in Function Space [140.792362459734]
  Diffusion models have recently emerged as a powerful framework for generative modeling. We introduce a mathematically rigorous framework called Denoising Diffusion Operators (DDOs) for training diffusion models in function space. We show that the corresponding discretized algorithm generates accurate samples at a fixed cost independent of the data resolution.
  arXiv  Detail & Related papers  (2023-02-14T23:50:53Z)
• Latent Variable Representation for Reinforcement Learning [131.03944557979725]
  It remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of model-based reinforcement learning. We provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle. In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models.
  arXiv  Detail & Related papers  (2022-12-17T00:26:31Z)
• Generalised Latent Assimilation in Heterogeneous Reduced Spaces with Machine Learning Surrogate Models [10.410970649045943]
  We develop a system which combines reduced-order surrogate models with a novel data assimilation technique. Generalised Latent Assimilation can benefit both the efficiency provided by the reduced-order modelling and the accuracy of data assimilation.
  arXiv  Detail & Related papers  (2022-04-07T15:13:12Z)
• Extension of Dynamic Mode Decomposition for dynamic systems with incomplete information based on t-model of optimal prediction [69.81996031777717]
  The Dynamic Mode Decomposition has proved to be a very efficient technique to study dynamic data. The application of this approach becomes problematic if the available data is incomplete because some dimensions of smaller scale either missing or unmeasured. We consider a first-order approximation of the Mori-Zwanzig decomposition, state the corresponding optimization problem and solve it with the gradient-based optimization method.
  arXiv  Detail & Related papers  (2022-02-23T11:23:59Z)
• Influence Estimation and Maximization via Neural Mean-Field Dynamics [60.91291234832546]
  We propose a novel learning framework using neural mean-field (NMF) dynamics for inference and estimation problems. Our framework can simultaneously learn the structure of the diffusion network and the evolution of node infection probabilities.
  arXiv  Detail & Related papers  (2021-06-03T00:02:05Z)
• A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models [93.24030378630175]
  We propose a novel numerical scheme to optimize the gradient flows for learning energy-based models (EBMs) We derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation. Compared with existing schemes, Wasserstein gradient flow is a smoother and near-optimal numerical scheme to approximate real data densities.
  arXiv  Detail & Related papers  (2019-10-31T02:26:20Z)

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.