LGNANAMLMar 25

Polynomial Speedup in Diffusion Models with the Multilevel Euler-Maruyama Method

arXiv:2603.2459463.5h-index: 16
Predicted impact top 33% in LG · last 90 daysOriginality Incremental advance
AI Analysis

This provides a polynomial speedup for diffusion model sampling, addressing efficiency issues in image generation, though it is incremental as it builds on existing Euler-Maruyama methods.

The paper tackles the computational bottleneck in diffusion models by introducing the Multilevel Euler-Maruyama method, which achieves polynomial speedups—up to fourfold on the CelebA dataset—by reducing the cost of solving SDEs to that of a single drift evaluation in the HTMC regime.

We introduce the Multilevel Euler-Maruyama (ML-EM) method compute solutions of SDEs and ODEs using a range of approximators $f^1,\dots,f^k$ to the drift $f$ with increasing accuracy and computational cost, only requiring a few evaluations of the most accurate $f^k$ and many evaluations of the less costly $f^1,\dots,f^{k-1}$. If the drift lies in the so-called Harder than Monte Carlo (HTMC) regime, i.e. it requires $ε^{-γ}$ compute to be $ε$-approximated for some $γ>2$, then ML-EM $ε$-approximates the solution of the SDE with $ε^{-γ}$ compute, improving over the traditional EM rate of $ε^{-γ-1}$. In other terms it allows us to solve the SDE at the same cost as a single evaluation of the drift. In the context of diffusion models, the different levels $f^{1},\dots,f^{k}$ are obtained by training UNets of increasing sizes, and ML-EM allows us to perform sampling with the equivalent of a single evaluation of the largest UNet. Our numerical experiments confirm our theory: we obtain up to fourfold speedups for image generation on the CelebA dataset downscaled to 64x64, where we measure a $γ\approx2.5$. Given that this is a polynomial speedup, we expect even stronger speedups in practical applications which involve orders of magnitude larger networks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes