Work

Convergence rates for generative drifting flows: fixed-scale obstructions and multihead acceleration

Year: 2026

Type: preprint

Abstract: Drifting models offer a promising route to faster generative AI: they perform gradual transport during training, while generating new samples in a single step. This paper asks whether the underlying drifting process can converge rapidly to a target distribution under ideal conditions, before finite-data or optimization effects are introduced. We show that its convergence rate depends critically on how it handles spatial scale. With a single fixed resolution, fine-scale features of the target can become nearly invisible, leading to extremely slow convergence. We introduce a multihead approach that combines scale-normalized information across a continuum of resolutions. We prove that this multihead approach restores exponential convergence near standard reference distributions. These results identify fixed resolution as a key bottleneck and provide a simple route to faster one-step generative models.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2609.15193

Authors: Stéphanovitch, Arthur, Aamari, Eddie

Institutions: Centre de Recherche en Économie et Statistique, ENSAE Paris, École Normale Supérieure

Language: English

Topic: Generative Adversarial Networks and Image Synthesis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7213230230

Cites:

Cited by:

Related to: