paper-with-me

Papers

Optimization-Free Diffusion Model -- A Perturbation Theory Approach

2025-05-29 · Yuehaw Khoo, Mathias Oster, Yifan Peng

Diffusion models have emerged as a powerful framework in generative modeling, typically relying on optimizing neural networks to estimate the score function via forward SDE simulations. In this work, we propose an alternative method that is both optimization-free and forward SDE-free. By expanding the score function in a sparse set of eigenbasis of the backward Kolmogorov operator associated with the diffusion process, we reformulate score estimation as the solution to a linear system, avoiding iterative optimization and time-dependent sample generation. We analyze the approximation error using perturbation theory and demonstrate the effectiveness of our method on high-dimensional Boltzmann distributions and real-world datasets.

📄 PDF Abstract BibTeX arXiv:2505.23652

Code (0)

등록된 구현이 없습니다.

Tasks

model

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…
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models

2026-05-12 · Ankit Yadav, Arpit Garg, Ta Duc Huy, Lingqiao Liu arxiv

Distilled one-step (T=1) or few-step (T$\leq$4) diffusion models enable real-time image generation but often exhibit reduced sample diversity compared to their multi-step counterparts. In multi-step diffusion, diversity …

Image Generation

Optimization-Free Image Immunization Against Diffusion-Based Editing

2024-11-27 · Tarik Can Ozden, Ozgur Kara, Oguzhan Akcin, Kerem Zaman 외

Current image immunization defense techniques against diffusion-based editing embed imperceptible noise in target images to disrupt editing models. However, these methods face scalability challenges, as they require time…

On the diffusion approximation of nonconvex stochastic gradient descent

2017-05-22 · Wenqing Hu, Chris Junchi Li, Lei LI, Jian-Guo Liu

We study the Stochastic Gradient Descent (SGD) method in nonconvex optimization problems from the point of view of approximating diffusion processes. We prove rigorously that the diffusion process can approximate the SGD…

Scale-free network optimization: foundations and algorithms

2016-02-12 · Patrick Rebeschini, Sekhar Tatikonda

We investigate the fundamental principles that drive the development of scalable algorithms for network optimization. Despite the significant amount of work on parallel and decentralized algorithms in the optimization co…

Sensitivity

Token Perturbation Guidance for Diffusion Models

2025-06-10 · Javad Rajabi, Soroush Mehraban, Seyedmorteza Sadat, Babak Taati

Classifier-free guidance (CFG) has become an essential component of modern diffusion models to enhance both generation quality and alignment with input conditions. However, CFG requires specific training procedures and i…