A Unified View of Drifting and Score-Based Models

• URL: http://arxiv.org/abs/2603.07514v1
• Date: Sun, 08 Mar 2026 07:41:36 GMT
• Title: A Unified View of Drifting and Score-Based Models
• Abstract summary: We make our relationship to the score-matching principle behind diffusion models precise by showing that drifting admits a score-based formulation on kernel-smoothed distributions.<n>We derive an exact decomposition for general radial kernels, and for the Laplace kernel we prove rigorous error bounds showing that drifting remains an accurate proxy for score matching in low-temperature and high-dimensional regimes.
• Score: 92.51878018325031
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Drifting models train one-step generators by optimizing a mean-shift discrepancy induced by a kernel between the data and model distributions, with Laplace kernels used by default in practice. At each point, this discrepancy compares the kernel-weighted displacement toward nearby data samples with the corresponding displacement toward nearby model samples, yielding a transport direction for generated samples. In this paper, we make its relationship to the score-matching principle behind diffusion models precise by showing that drifting admits a score-based formulation on kernel-smoothed distributions. For Gaussian kernels, the population mean-shift field coincides with the score difference between the Gaussian-smoothed data and model distributions. This identity follows from Tweedie's formula, which links the score of a Gaussian-smoothed density to the corresponding conditional mean, and implies that Gaussian-kernel drifting is exactly a score-matching-style objective on smoothed distributions. It also clarifies the connection to Distribution Matching Distillation (DMD): both methods use score-mismatch transport directions, but drifting realizes the score signal nonparametrically from kernel neighborhoods, whereas DMD uses a pretrained diffusion teacher. Beyond Gaussians, we derive an exact decomposition for general radial kernels, and for the Laplace kernel we prove rigorous error bounds showing that drifting remains an accurate proxy for score matching in low-temperature and high-dimensional regimes.

Related papers

• Constrained Diffusion Models with Primal-Dual Inference [76.64466170898369]
  We develop constrained diffusion models with primal-dual inference (PDI)<n>PDI infers the optimal primal distribution and its parametrizing dual variable.<n>We evaluate PDI on constrained sampling from a mixture of Gaussians, wireless resource allocation, and portfolio management.
  arXiv  Detail & Related papers  (2026-06-15T18:32:33Z)
• From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models [58.02657021435213]
  We propose a novel Gibbs-based corrector for discrete diffusion models, termed Gibbs-Accelerated Discrete Diffusion (GADD)<n>We show GADD achieves an overall sampling complexity of $mathcalO(mathrmpolylog (varepsilon-1)$, yielding the first such rate for diffusion-based samplers for uniform-rate discrete diffusion models.
  arXiv  Detail & Related papers  (2026-05-26T17:52:28Z)
• Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study [3.265950484493743]
  Diffusion models can be prone to memorization.<n>Regularization on the score has the same effect as increasing the size of the training dataset.<n>This perspective highlights two regularization mechanisms taking place in denoising diffusions.
  arXiv  Detail & Related papers  (2025-05-28T20:22:18Z)
• The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and its Applications [1.8416014644193066]
  We compare learned neural scores to the scores of two kinds of analytically tractable distributions.<n>We claim that the learned neural score is dominated by its linear (Gaussian) approximation for moderate to high noise scales.<n>We show that this allows the skipping of the first 15-30% of sampling steps while maintaining high sample quality.
  arXiv  Detail & Related papers  (2024-12-12T21:31:27Z)
• On the Wasserstein Convergence and Straightness of Rectified Flow [54.580605276017096]
  Rectified Flow (RF) is a generative model that aims to learn straight flow trajectories from noise to data.<n>We provide a theoretical analysis of the Wasserstein distance between the sampling distribution of RF and the target distribution.<n>We present general conditions guaranteeing uniqueness and straightness of 1-RF, which is in line with previous empirical findings.
  arXiv  Detail & Related papers  (2024-10-19T02:36:11Z)
• 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)
• Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models [59.331993845831946]
  Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. This paper provides the first theoretical study towards understanding the influence of guidance on diffusion models in the context of Gaussian mixture models.
  arXiv  Detail & Related papers  (2024-03-03T23:15:48Z)
• Adaptive Annealed Importance Sampling with Constant Rate Progress [68.8204255655161]
  Annealed Importance Sampling (AIS) synthesizes weighted samples from an intractable distribution. We propose the Constant Rate AIS algorithm and its efficient implementation for $alpha$-divergences.
  arXiv  Detail & Related papers  (2023-06-27T08:15:28Z)
• Deep Generative Learning via Schr\"{o}dinger Bridge [14.138796631423954]
  We learn a generative model via entropy with a Schr"odinger Bridge. We show that the generative model via Schr"odinger Bridge is comparable with state-of-the-art GANs.
  arXiv  Detail & Related papers  (2021-06-19T03:35:42Z)

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.