pith. sign in

arxiv: 2606.10353 · v1 · pith:KWI6S24Snew · submitted 2026-06-09 · 🧮 math.NA · cs.NA· math.ST· stat.TH

Higher-order Diffusion Sampling via Chebyshev Interpolation and Gauss--Seidel Iterations

classification 🧮 math.NA cs.NAmath.STstat.TH
keywords higher-orderscorediffusiondistributionguaranteeiterationsnon-asymptoticsampler
0
0 comments X
read the original abstract

Higher-order ODE solvers have shown strong empirical promise for accelerating diffusion models through the probability flow ODE, but rigorous non-asymptotic guarantees for such acceleration remain limited. In this paper, we develop a Chebyshev--Gauss--Seidel higher-order sampler and establish a non-asymptotic convergence guarantee that allows the approximation order to grow logarithmically with the number of outer iterations. In the exact-score setting, up to logarithmic factors, the proposed sampler requires at most \[ d^{1+o_T(1)}\varepsilon^{-1/K_1} \] score functions to approximate the target distribution on \(\mathbb{R}^d\) within total variation distance \(\varepsilon\), where \(o_T(1)\to 0\) as \(T\to\infty\) and \(K_1>0\) is a sufficiently large constant. The analysis assumes only a polynomial second-moment bound on the target distribution, thereby relaxing the bounded-support condition imposed in existing higher-order theory. Moreover, the guarantee is robust to score and Jacobian estimation errors and does not require higher-order smoothness assumptions on the score estimates. Numerical experiments on anisotropic Gaussian mixture benchmarks support the predicted improvement in the accuracy--cost tradeoff under finite score-evaluation budgets.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.