One-Step Diffusion Samplers via Self-Distillation and Deterministic Flow

• URL: http://arxiv.org/abs/2512.05251v1
• Date: Thu, 04 Dec 2025 20:57:53 GMT
• Title: One-Step Diffusion Samplers via Self-Distillation and Deterministic Flow
• Authors: Pascal Jutras-Dube, Jiaru Zhang, Ziran Wang, Ruqi Zhang,
• Abstract summary: Existing sampling algorithms typically require many iterative steps to produce high-quality samples.<n>We introduce one-step diffusion samplers which learn a step-conditioned ODE.<n>We show that standard ELBO estimates degrade in the few-step regime because common discrete yield mismatched forward/backward transition kernels.
• Score: 24.67443222055996
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sampling from unnormalized target distributions is a fundamental yet challenging task in machine learning and statistics. Existing sampling algorithms typically require many iterative steps to produce high-quality samples, leading to high computational costs. We introduce one-step diffusion samplers which learn a step-conditioned ODE so that one large step reproduces the trajectory of many small ones via a state-space consistency loss. We further show that standard ELBO estimates in diffusion samplers degrade in the few-step regime because common discrete integrators yield mismatched forward/backward transition kernels. Motivated by this analysis, we derive a deterministic-flow (DF) importance weight for ELBO estimation without a backward kernel. To calibrate DF, we introduce a volume-consistency regularization that aligns the accumulated volume change along the flow across step resolutions. Our proposed sampler therefore achieves both sampling and stable evidence estimate in only one or few steps. Across challenging synthetic and Bayesian benchmarks, it achieves competitive sample quality with orders-of-magnitude fewer network evaluations while maintaining robust ELBO estimates.

Related papers

• Initialization-Aware Score-Based Diffusion Sampling [2.554905387213586]
  classical samplers from a Gaussian distribution require a long time horizon noising typically inducing a large number of discretization steps and high computational cost.<n>We present a Kullback-Leibler convergence analysis of Vari Exploding diffusion samplers that highlights the critical role of the backward process.<n>Experiments on toy distributions and benchmark datasets demonstrate competitive or improved generative quality while using significantly fewer sampling steps.
  arXiv  Detail & Related papers  (2026-02-28T18:37:10Z)
• Sharp Convergence Rates for Masked Diffusion Models [53.117058231393834]
  We develop a total-variation based analysis for the Euler method that overcomes limitations.<n>Our results relax assumptions on score estimation, improve parameter dependencies, and establish convergence guarantees.<n>Overall, our analysis introduces a direct TV-based error decomposition along the CTMC trajectory and a decoupling-based path-wise analysis for FHS.
  arXiv  Detail & Related papers  (2026-02-26T00:47:51Z)
• Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models [100.28111930893188]
  Some of today's best generative models still require hundreds to thousands of neural function evaluations to compute a single likelihood.<n>We present fast flow joint distillation (F2D2), a framework that simultaneously reduces the number of NFEs required for both sampling and likelihood evaluation by two orders of magnitude.<n>F2D2 is modular, compatible with existing flow-based few-step sampling models, and requires only an additional divergence prediction head.
  arXiv  Detail & Related papers  (2025-12-02T10:48:20Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• Quantizing Diffusion Models from a Sampling-Aware Perspective [43.95032520555463]
  We propose a sampling-aware quantization strategy, wherein a Mixed-Order Trajectory Alignment technique is devised.<n>Experiments on sparse-step fast sampling across multiple datasets demonstrate that our approach preserves the rapid convergence characteristics of high-speed samplers.
  arXiv  Detail & Related papers  (2025-05-04T20:50:44Z)
• Single-Step Consistent Diffusion Samplers [8.758218443992467]
  Existing sampling algorithms typically require many iterative steps to produce high-quality samples.<n>We introduce consistent diffusion samplers, a new class of samplers designed to generate high-fidelity samples in a single step.<n>We show that our approach yields high-fidelity samples using less than 1% of the network evaluations required by traditional diffusion samplers.
  arXiv  Detail & Related papers  (2025-02-11T14:25:52Z)
• Neural Flow Samplers with Shortcut Models [19.81513273510523]
  Continuous flow-based neural samplers offer a promising approach to generate samples from unnormalized densities.<n>We introduce an improved estimator for these challenging quantities, employing a velocity-driven Sequential Monte Carlo method.<n>Our proposed Neural Flow Shortcut Sampler empirically outperforms existing flow-based neural samplers on both synthetic datasets and complex n-body system targets.
  arXiv  Detail & Related papers  (2025-02-11T07:55:41Z)
• Distributional Diffusion Models with Scoring Rules [83.38210785728994]
  Diffusion models generate high-quality synthetic data.<n> generating high-quality outputs requires many discretization steps.<n>We propose to accomplish sample generation by learning the posterior em distribution of clean data samples.
  arXiv  Detail & Related papers  (2025-02-04T16:59:03Z)
• Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations [53.180374639531145]
  Self-Refining Diffusion Samplers (SRDS) retain sample quality and can improve latency at the cost of additional parallel compute.<n>We take inspiration from the Parareal algorithm, a popular numerical method for parallel-in-time integration of differential equations.
  arXiv  Detail & Related papers  (2024-12-11T11:08:09Z)
• SITCOM: Step-wise Triple-Consistent Diffusion Sampling for Inverse Problems [14.2814208019426]
  Diffusion models (DMs) are a class of generative models that allow sampling from a distribution learned over a training set.<n>We state three conditions for achieving measurement-consistent diffusion trajectories.<n>We propose a new optimization-based sampling method that not only enforces standard data manifold measurement consistency and forward diffusion consistency, but also incorporates our proposed step-wise and network-regularized backward diffusion consistency.
  arXiv  Detail & Related papers  (2024-10-06T13:39:36Z)
• Unrolling Particles: Unsupervised Learning of Sampling Distributions [102.72972137287728]
  Particle filtering is used to compute good nonlinear estimates of complex systems. We show in simulations that the resulting particle filter yields good estimates in a wide range of scenarios.
  arXiv  Detail & Related papers  (2021-10-06T16:58:34Z)

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.