Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds

2026-05-15 · Guoji Fu, Taiji Suzuki, Wee Sun Lee, Atsushi Nitanda arxiv

Score-based generative models are trained in high-dimensional ambient spaces, yet many data distributions are supported on low-dimensional nonlinear structures. We prove that, for compact $d$-dimensional smooth manifolds $\mathcal{M} \subset [0,1]^D$ with $d > 2$ and $β$-Hölder densities strictly positive on $\mathcal{M}$, a variance-preserving SGM estimator attains the intrinsic Wasserstein--1 sample exponent $\tilde{\mathcal{O}}(D^{\mathcal{O}_β(d)}n^{-(β+1)/(d+2β)})$, up to logarithmic factors and explicit geometry and density factors. The full nonasymptotic bound explicitly isolates the finite-order geometry envelope, Hölder radius, density lower bound, ambient dependence, and finite-order correction terms. The analysis separates score approximation into a large-noise tangent-cell regime and a small-noise projection-centered, de-Gaussianized Laplace regime. The key technical ingredient is a ReLU implementation of nearest-projection coordinates via finite intrinsic anchors and Gauss--Newton iterations, rather than approximating the manifold projection as a black-box high-dimensional smooth map. Consequently, for families with polynomially controlled geometry and density lower bounds, the constructed score-network parameters have polynomial ambient dependence.

📄 PDF Abstract BibTeX arXiv:2605.15822

Code (0)

등록된 구현이 없습니다.

Generalization Properties of Score-matching Diffusion Models for Intrinsically Low-dimensional Data

2026-03-04 · Saptarshi Chakraborty, Quentin Berthet, Peter L. Bartlett arxiv

Despite the remarkable empirical success of score-based diffusion models, their statistical guarantees remain underdeveloped. Existing analyses often provide pessimistic convergence rates that do not reflect the intrinsi…

Manifold-Aligned Generative Transport

2026-02-23 · Xinyu Tian, Xiaotong Shen arxiv

High-dimensional generative modeling is fundamentally a manifold-learning problem: real data concentrate near a low-dimensional structure embedded in the ambient space. Effective generators must therefore balance support…

Reflected diffusion models adapt to low-dimensional data

2026-03-25 · Asbjørn Holk, Claudia Strauch, Lukas Trottner arxiv

While the mathematical foundations of score-based generative models are increasingly well understood for unconstrained Euclidean spaces, many practical applications involve data restricted to bounded domains. This paper …

Wasserstein Convergence Guarantees for a General Class of Score-Based Generative Models

2023-11-18 · Xuefeng Gao, Hoang M. Nguyen, Lingjiong Zhu

Score-based generative models (SGMs) is a recent class of deep generative models with state-of-the-art performance in many applications. In this paper, we establish convergence guarantees for a general class of SGMs in 2…

Image Generation Unconditional Image Generation

Adversarial Intrinsic Motivation for Reinforcement Learning

2021-05-27 · NeurIPS 2021 12 · Ishan Durugkar, Mauricio Tec, Scott Niekum, Peter Stone

Learning with an objective to minimize the mismatch with a reference distribution has been shown to be useful for generative modeling and imitation learning. In this paper, we investigate whether one such objective, the …

Multi-Goal Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)