Authors
- Yong-Hyun Park
- Chieh-Hsin Lai
- Satoshi Hayakawa
- Yuhta Takida
- Yuki Mitsufuji
Venue
- ICLR-25
Date
- 2025
Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models
Yong-Hyun Park
Satoshi Hayakawa
ICLR-25
2025
Abstract
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
-leaping accelerate this process, they introduce 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 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.
Related Publications
We present Music Arena, an open platform for scalable human preference evaluation of text-to-music (TTM) models. Soliciting human preferences via listening studies is the gold standard for evaluation in TTM, but these studies are expensive to conduct and difficult to compare…
This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specific training data points contributed to the generation of a particular output from a specific mod…
Blind inverse problems, where both the target data and forward operator are unknown, are crucial to many computer vision applications. Existing methods often depend on restrictive assumptions such as additional training, operator linearity, or narrow image distributions, thu…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.