Research

Paper

AI LLM March 02, 2026

Constrained Particle Seeking: Solving Diffusion Inverse Problems with Just Forward Passes

Authors

Hongkun Dou, Zike Chen, Zeyu Li, Hongjue Li, Lijun Yang, Yue Deng

Abstract

Diffusion models have gained prominence as powerful generative tools for solving inverse problems due to their ability to model complex data distributions. However, existing methods typically rely on complete knowledge of the forward observation process to compute gradients for guided sampling, limiting their applicability in scenarios where such information is unavailable. In this work, we introduce \textbf{\emph{Constrained Particle Seeking (CPS)}}, a novel gradient-free approach that leverages all candidate particle information to actively search for the optimal particle while incorporating constraints aligned with high-density regions of the unconditional prior. Unlike previous methods that passively select promising candidates, CPS reformulates the inverse problem as a constrained optimization task, enabling more flexible and efficient particle seeking. We demonstrate that CPS can effectively solve both image and scientific inverse problems, achieving results comparable to gradient-based methods while significantly outperforming gradient-free alternatives. Code is available at https://github.com/deng-ai-lab/CPS.

Metadata

arXiv ID: 2603.01837
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-03-02
Fetched: 2026-03-03 04:34

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.01837v1</id>\n    <title>Constrained Particle Seeking: Solving Diffusion Inverse Problems with Just Forward Passes</title>\n    <updated>2026-03-02T13:15:49Z</updated>\n    <link href='https://arxiv.org/abs/2603.01837v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.01837v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Diffusion models have gained prominence as powerful generative tools for solving inverse problems due to their ability to model complex data distributions. However, existing methods typically rely on complete knowledge of the forward observation process to compute gradients for guided sampling, limiting their applicability in scenarios where such information is unavailable. In this work, we introduce \\textbf{\\emph{Constrained Particle Seeking (CPS)}}, a novel gradient-free approach that leverages all candidate particle information to actively search for the optimal particle while incorporating constraints aligned with high-density regions of the unconditional prior. Unlike previous methods that passively select promising candidates, CPS reformulates the inverse problem as a constrained optimization task, enabling more flexible and efficient particle seeking. We demonstrate that CPS can effectively solve both image and scientific inverse problems, achieving results comparable to gradient-based methods while significantly outperforming gradient-free alternatives. Code is available at https://github.com/deng-ai-lab/CPS.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='stat.ML'/>\n    <published>2026-03-02T13:15:49Z</published>\n    <arxiv:comment>Accepted by AAAI 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Hongkun Dou</name>\n    </author>\n    <author>\n      <name>Zike Chen</name>\n    </author>\n    <author>\n      <name>Zeyu Li</name>\n    </author>\n    <author>\n      <name>Hongjue Li</name>\n    </author>\n    <author>\n      <name>Lijun Yang</name>\n    </author>\n    <author>\n      <name>Yue Deng</name>\n    </author>\n  </entry>"
}