Generative Drifting is Secretly Score Matching: a Spectral and Variational Perspective

TL;DR

This paper reveals that generative drifting with Gaussian kernels is fundamentally score matching, providing new theoretical insights, convergence analysis, and practical training strategies for improved generative models.

Contribution

It establishes the connection between drifting and score matching, explains the role of kernels and stop-gradient, and introduces a spectral and variational framework for analysis.

Findings

Drift operator equals score difference on smoothed distributions with Gaussian kernels.

Exponential high-frequency bottleneck explains kernel preference, with Laplacian kernel performing better.

Proposed exponential bandwidth schedule significantly accelerates convergence.

Abstract

Generative Modeling via Drifting has recently achieved state-of-the-art one-step image generation through a kernel-based drift operator, yet the success is largely empirical and its theoretical foundations remain poorly understood. In this paper, we make the following observation: \emph{under a Gaussian kernel, the drift operator is exactly a score difference on smoothed distributions}. This insight allows us to answer all three key questions left open in the original work: (1) whether a vanishing drift guarantees equality of distributions ($V_{p,q}=0\Rightarrow p=q$), (2) how to choose between kernels, and (3) why the stop-gradient operator is indispensable for stable training. Our observations position drifting within the well-studied score-matching family and enable a rich theoretical perspective. By linearizing the McKean-Vlasov dynamics and probing them in Fourier space, we reveal frequency-dependent convergence timescales comparable to \emph{Landau damping} in plasma kinetic theory: the Gaussian kernel suffers an exponential high-frequency bottleneck, explaining the empirical preference for the Laplacian kernel. We also propose an exponential bandwidth annealing schedule $\sigma(t)=\sigma_0 e^{-rt}$ that reduces convergence time from $\exp(O(K_{\max}^2))$ to $O(\log K_{\max})$. Finally, by formalizing drifting as a Wasserstein gradient flow of the smoothed KL divergence, we prove that the stop-gradient operator is derived directly from the frozen-field discretization mandated by the JKO scheme, and removing it severs training from any gradient-flow guarantee. This variational perspective further provides a general template for constructing novel drift operators, demonstrated with a Sinkhorn divergence drift.