paper-with-me

Papers

The probability flow ODE is provably fast

2023-05-19 · NeurIPS 2023 11

We provide the first polynomial-time convergence guarantees for the probability flow ODE implementation (together with a corrector step) of score-based generative modeling. Our analysis is carried out in the wake of recent results obtaining such guarantees for the SDE-based implementation (i.e., denoising diffusion probabilistic modeling or DDPM), but requires the development of novel techniques for studying deterministic dynamics without contractivity. Through the use of a specially chosen corrector step based on the underdamped Langevin diffusion, we obtain better dimension dependence than prior works on DDPM ($O(\sqrt{d})$ vs. $O(d)$, assuming smoothness of the data distribution), highlighting potential advantages of the ODE framework.

📄 PDF Abstract BibTeX arXiv:2305.11798

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Provably convergent quasistatic dynamics for mean-field two-player zero-sum games

2022-02-15 · ICLR 2022 4 · Chao Ma, Lexing Ying

In this paper, we study the problem of finding mixed Nash equilibrium for mean-field two-player zero-sum games. Solving this problem requires optimizing over two probability distributions. We consider a quasistatic Wasse…

Temporal Pair Consistency for Variance-Reduced Flow Matching

2026-02-04 · Chika Maduabuchi, Jindong Wang arxiv

Continuous-time generative models, such as diffusion models, flow matching, and rectified flow, learn time-dependent vector fields but are typically trained with objectives that treat timesteps independently, leading to …

Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithm

2020-02-12 · NeurIPS 2020 12 · Tianyi Lin, Nhat Ho, Xi Chen, Marco Cuturi 외

We study the fixed-support Wasserstein barycenter problem (FS-WBP), which consists in computing the Wasserstein barycenter of $m$ discrete probability measures supported on a finite metric space of size $n$. We show firs…

Open-Ended Question Answering

Fast Inference and Update of Probabilistic Density Estimation on Trajectory Prediction

2023-08-17 · ICCV 2023 1 · Takahiro Maeda, Norimichi Ukita

Safety-critical applications such as autonomous vehicles and social robots require fast computation and accurate probability density estimation on trajectory prediction. To address both requirements, this paper presents …

Autonomous VehiclesDensity EstimationPredictionTrajectory Prediction

Towards High-Order Mean Flow Generative Models: Feasibility, Expressivity, and Provably Efficient Criteria

2025-08-09 · Yang Cao, Yubin Chen, Zhao Song, Jiahao Zhang arxiv

Generative modelling has seen significant advances through simulation-free paradigms such as Flow Matching, and in particular, the MeanFlow framework, which replaces instantaneous velocity fields with average velocities …