Connections between the Föllmer process and the denoising diffusion probabilistic model

Yuta Koike

stat.MLMay 18, 2026

Connections between the Föllmer process and the denoising diffusion probabilistic model

Authors: Yuta Koike

Organizations: *Graduate School of Mathematical Sciences, University of Tokyo · †CREST, Japan Science and Technology Agency

Abstract

The Föllmer process is a Brownian motion conditioned to have a pre-specified distribution at time 1. This process can be interpreted as an ``augmented'' time-compressed version of the reverse stochastic differential equation (SDE) corresponding to the denoising diffusion probabilistic model (DDPM). While this fact has been indirectly used to analyze DDPM sampling errors via discretization of the reverse SDE, the connection between direct discretization of the Föllmer process and the DDPM sampler has not yet been fully explored. This paper clarifies this point while surveying relevant results from the literature. We show that discretized Föllmer processes give natural hyper-parameter settings of the DDPM sampler while accommodating a broader class of variance schedules than discretized reverse SDEs. Moreover, this allows us to systematically recover state-of-the-art results on DDPM sampling error bounds, along with slight improvements.

Explore similar work

Wasserstein bounds for denoising diffusion probabilistic models via the Föllmer process
May 18, 2026Yuta KoikeWasserstein Distance Logarithmic Sobolev Inequalities
Why DDIM Hallucinates More Than DDPM: A Theoretical Analysis of Reverse Dynamics
May 7, 2026Muhammad H. Ashiq, Samanyu Arora, Abhinav N. Harish +3Diffusion Sampling Denoising Diffusion Probabilistic Model
Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster
May 18, 2026Grigory Bartosh, Teodora Pandeva, Sushrut Karmalkar +1Generative Models Factor

May 18, 2026 · stat.MLJ/K move · Enter open · S save

Wasserstein bounds for denoising diffusion probabilistic models via the Föllmer process

Yuta Koike

*Graduate School of Mathematical Sciences, University of Tokyo · †CREST, Japan Science and Technology Agency

This paper studies sampling error bounds for denoising diffusion probabilistic models (DDPMs) in the 2-Wasserstein distance. Our contributions are threefold. (i) Under general Lipschitz-type conditions on the score function and for a broad class of variance schedules, including the cosine schedule, we establish sharp upper bounds that are optimal in both the dimension and the number of steps, and recover several sharp error bounds previously obtained in the literature. (ii) We prove that the same Lipschitz-type conditions, which encompass those commonly imposed on the (learned) score, imply a logarithmic Sobolev inequality and hence a quadratic transportation cost inequality for the DDPM. As a consequence, in settings covered by existing work, an optimal Wasserstein bound, up to a logarithmic factor, follows from the recently obtained sharp error bound in the Kullback-Leibler divergence under geometric-type variance schedules. (iii) We show that for general log-concave target distributions, the optimal Wasserstein error bound remains attainable even without a quadratic transportation cost inequality for the target. Our analysis is based on viewing the DDPM sampler as a discretization of the Föllmer process rather than the conventional reverse Ornstein-Uhlenbeck process.

Wasserstein Distance Logarithmic Sobolev Inequalities

Open paper Ask about it PDF

Abstract

Explore similar work

Wasserstein bounds for denoising diffusion probabilistic models via the Föllmer process

Why DDIM Hallucinates More Than DDPM: A Theoretical Analysis of Reverse Dynamics

Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster