Flow Sampling: Learning to Sample from Unnormalized Densities via Denoising Conditional Processes

• URL: http://arxiv.org/abs/2605.03984v1
• Date: Tue, 05 May 2026 17:07:37 GMT
• Title: Flow Sampling: Learning to Sample from Unnormalized Densities via Denoising Conditional Processes
• Abstract summary: Flow Sampling is a framework built on diffusion models and flow matching for the data-free setting.<n>We utilize the interpolant process to minimize the number of energy function evaluations during training, resulting in an efficient and scalable method for sampling unnormalized densities.
• Score: 8.197659010420418
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sampling from unnormalized densities is analogous to the generative modeling problem, but the target distribution is defined by a known energy function instead of data samples. Because evaluating the energy function is often costly, a primary challenge is to learn an efficient sampler. We introduce Flow Sampling, a framework built on diffusion models and flow matching for the data-free setting. Our training objective is conditioned on a noise sample and regresses onto a denoising diffusion drift constructed from the energy function. In contrast, diffusion models' objective is conditioned on a data sample and regresses onto a noising diffusion drift. We utilize the interpolant process to minimize the number of energy function evaluations during training, resulting in an efficient and scalable method for sampling unnormalized densities. Furthermore, our formulation naturally extends to Riemannian manifolds, enabling diffusion-based sampling in geometries beyond Euclidean space. We derive a closed-form formula for the conditional drift on constant curvature manifolds, including hyperspheres and hyperbolic spaces. We evaluate Flow Sampling on synthetic energy benchmarks, small peptides, large-scale amortized molecular conformer generation, and distributions supported on the sphere, demonstrating strong empirical performance.

Related papers

• Self-Augmented Diffusion Guidance for Physics-Informed Generation [3.686108263907984]
  We propose a simple yet effective physics-informed approach based on diffusion guidance with self-generated data.<n>The proposed method learns the data distribution conditioned on the degree of deviation from the physically correct dynamics and generates samples by explicitly setting the deviation condition to be zero.<n> Experimental results demonstrate that the proposed model not only significantly reduces the limitation compared with standard diffusion models but also achieves further reductions when combined with existing physics-constrained diffusion methods.
  arXiv  Detail & Related papers  (2026-08-27T07:44:03Z)
• Training-Free Generative Sampling via Moment-Matched Score Smoothing [0.6015898117103069]
  Diffusion models generate samples by denoising along the score of a perturbed target distribution.<n>Recent work suggests that score matching implicitly smooths the empirical score.<n>We propose moment-matched score-smoothed overdamped Langevin dynamics.
  arXiv  Detail & Related papers  (2026-05-14T02:20:36Z)
• Discrete Diffusion with Sample-Efficient Estimators for Conditionals [2.7400724993677703]
  We study a discrete denoising diffusion framework that integrates a sample-efficient estimator of single-site conditionals with round-robin noising and denoising dynamics.<n>We employ a sample-efficient method known as Neural Interaction Screening Estimator (NeurISE) to estimate these conditionals in the diffusion dynamics.<n> Controlled experiments on synthetic Ising models, MNIST, and scientific data sets produced by a D-Wave quantum annealer, synthetic Potts model and one-dimensional quantum systems demonstrate the proposed approach.
  arXiv  Detail & Related papers  (2026-02-23T19:20:37Z)
• Enhancing Diffusion-Based Sampling with Molecular Collective Variables [23.394068689634086]
  Diffusion-based samplers learn to sample complex, high-dimensional distributions using energies or log densities alone.<n>We introduce a sequential bias along bespoke, information-rich, low-dimensional projections of atomic coordinates known as collective variables (CVs)<n>We are the first to demonstrate reactive sampling using a diffusion-based sampler, capturing bond breaking and formation with universal interatomic potentials at near-first-principles accuracy.
  arXiv  Detail & Related papers  (2025-10-13T20:44:54Z)
• Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities [93.13866975467549]
  We propose Progressive Inference-Time Annealing (PITA) to learn diffusion-based samplers.<n>PITA combines two complementary techniques: Annealing of the Boltzmann distribution and Diffusion smoothing.<n>It enables equilibrium sampling of N-body particle systems, Alanine Dipeptide, and tripeptides in Cartesian coordinates.
  arXiv  Detail & Related papers  (2025-06-19T17:14:22Z)
• Resolving Memorization in Empirical Diffusion Model for Manifold Data in High-Dimensional Spaces [5.716752583983991]
  When the data distribution consists of n points, empirical diffusion models tend to reproduce existing data points.<n>This work shows that the memorization issue can be solved simply by applying an inertia update at the end of the empirical diffusion simulation.<n>We demonstrate that the distribution of samples from this model approximates the true data distribution on a $C2$ manifold of dimension $d$, within a Wasserstein-1 distance of order $O(n-frac2d+4)$.
  arXiv  Detail & Related papers  (2025-05-05T09:40:41Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Boosting Diffusion Models with Moving Average Sampling in Frequency Domain [101.43824674873508]
  Diffusion models rely on the current sample to denoise the next one, possibly resulting in denoising instability. In this paper, we reinterpret the iterative denoising process as model optimization and leverage a moving average mechanism to ensemble all the prior samples. We name the complete approach "Moving Average Sampling in Frequency domain (MASF)"
  arXiv  Detail & Related papers  (2024-03-26T16:57:55Z)
• Iterated Denoising Energy Matching for Sampling from Boltzmann Densities [109.23137009609519]
  Iterated Denoising Energy Matching (iDEM) iDEM alternates between (I) sampling regions of high model density from a diffusion-based sampler and (II) using these samples in our matching objective. We show that the proposed approach achieves state-of-the-art performance on all metrics and trains $2-5times$ faster.
  arXiv  Detail & Related papers  (2024-02-09T01:11:23Z)
• A Geometric Perspective on Diffusion Models [57.27857591493788]
  We inspect the ODE-based sampling of a popular variance-exploding SDE. We establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm.
  arXiv  Detail & Related papers  (2023-05-31T15:33:16Z)
• Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces [0.0]
  We develop a theoretical formulation for arbitrary discrete-state Markov processes in the forward diffusion process. As an example, we introduce Blackout Diffusion'', which learns to produce samples from an empty image instead of from noise.
  arXiv  Detail & Related papers  (2023-05-18T16:24:12Z)
• ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories [144.03939123870416]
  We propose a novel conditional diffusion model by introducing conditions into the forward process. We use extra latent space to allocate an exclusive diffusion trajectory for each condition based on some shifting rules. We formulate our method, which we call textbfShiftDDPMs, and provide a unified point of view on existing related methods.
  arXiv  Detail & Related papers  (2023-02-05T12:48:21Z)

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.