paper-with-me

Papers

$\textit{Jump Your Steps}$: Optimizing Sampling Schedule of Discrete Diffusion Models

2024-10-10 · Yong-Hyun Park, Chieh-Hsin Lai, Satoshi Hayakawa, Yuhta Takida, Yuki Mitsufuji

Diffusion models have seen notable success in continuous domains, leading to the development of discrete diffusion models (DDMs) for discrete variables. Despite recent advances, DDMs face the challenge of slow sampling speeds. While parallel sampling methods like $\tau$-leaping accelerate this process, they introduce $\textit{Compounding Decoding Error}$ (CDE), where discrepancies arise between the true distribution and the approximation from parallel token generation, leading to degraded sample quality. In this work, we present $\textit{Jump Your Steps}$ (JYS), a novel approach that optimizes the allocation of discrete sampling timesteps by minimizing CDE without extra computational cost. More precisely, we derive a practical upper bound on CDE and propose an efficient algorithm for searching for the optimal sampling schedule. Extensive experiments across image, music, and text generation show that JYS significantly improves sampling quality, establishing it as a versatile framework for enhancing DDM performance for fast sampling.

📄 PDF Abstract BibTeX arXiv:2410.07761

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

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

Align Your Steps: Optimizing Sampling Schedules in Diffusion Models

2024-04-22 · Amirmojtaba Sabour, Sanja Fidler, Karsten Kreis

Diffusion models (DMs) have established themselves as the state-of-the-art generative modeling approach in the visual domain and beyond. A crucial drawback of DMs is their slow sampling speed, relying on many sequential …

Optimize Your Sampling: Tuned Diffusion Sampling with Bayesian Optimization

2026-08-18 · Travis Zhang, Christian Belardi, Justin Lovelace, Jin Peng Zhou 외 arxiv

Sampling from a diffusion model typically requires many forward passes through a large neural network, making generation computationally expensive. While much work has focused on efficient solvers and samplers, comparati…

Text-to-Image Generation

Deep ZakaiJ: Structured Filtering for Jump-Diffusion Time Series Forecasting

2026-05-23 · Yan Leng, Thibaut Mastrolia, Hao Wang arxiv

Time series driven by unobserved latent states frequently exhibit abrupt jump discontinuities whose timing and magnitude cannot be predicted from observed history alone. Classical jump-diffusion models offer a principled…

Time Series Forecasting

Neural Empirical Bayes

2019-03-06 · Saeed Saremi, Aapo Hyvarinen

We unify $\textit{kernel density estimation}$ and $\textit{empirical Bayes}$ and address a set of problems in unsupervised learning with a geometric interpretation of those methods, rooted in the $\textit{concentration o…

DenoisingDensity Estimation

Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction

2026-04-17 · Jingyuan Li, Xiaoyi Jiang, Fukang Wen, Wei Liu 외 arxiv

Discrete diffusion models based on continuous-time Markov chains (CTMCs) have shown strong performance on language and discrete data generation, yet existing approaches typically parameterize the reverse rate matrix mono…