Provable diffusion-based posterior sampling for linear inverse problems via DDIM
Yuchen Jiao, Na Li, Changxiao Cai, Yuxin Chen, Gen Li
cs.LG, cs.AI, stat.ML
Submitted: 2026-07-21
License: http://creativecommons.org/licenses/by/4.0/
The gist: Diffusion-based methods have achieved remarkable empirical success in solving inverse problems.
Terminology
Abstract
Diffusion-based methods have achieved remarkable empirical success in solving inverse problems. However, many existing posterior samplers either lack rigorous theoretical guarantees or incur substantial computational overhead. We propose a simple and efficient algorithm, called, for solving linear inverse problems with diffusion priors via a DDIM-type sampler. Our method requires only lightweight, coordinate-wise modifications to the standard DDIM update, while explicitly incorporating the measurement model. The key idea is to perform posterior sampling separately along each singular direction of the measurement operator: for each direction, the sampler follows the learned diffusion prior when the observation signal-to-noise ratio (SNR) is below the corresponding diffusion SNR, and switches to a calibrated measurement-based predictor otherwise. We prove that the proposed sampler converges to the Bayesian posterior conditioned on the measurements. Empirical results show that the proposed sampler performs favorably against existing diffusion-based posterior samplers across a range of image restoration tasks, achieving the best performance on the majority of evaluation metrics considered. Overall, our results convert posterior sampling for noisy linear inverse problems to simple coordinate-wise DDIM updates, yielding an efficient, easy-to-implement algorithm with provable posterior consistency.
Sources
- Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices
- Monte Carlo guided Diffusion for Bayesian linear inverse problems
- ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models
- Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems
- A Survey on Diffusion Models for Inverse Problems
- Diffusion models as plug-and-play priors
- Diffusion Posterior Sampling is Computationally Intractable
- Convergence Analysis of Probability Flow ODE for Score-based Generative Models
- Instance-dependent Convergence Theory for Diffusion Models
- Optimal Convergence Analysis of DDPM for General Distributions
- The Principles of Diffusion Models
- A Sharp Convergence Theory for The Probability Flow ODEs of Diffusion Models
- Low-dimensional adaptation of diffusion models: Convergence in total variation
- DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
- A Variational Perspective on Solving Inverse Problems with Diffusion Models
- SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
- Score-Based Generative Modeling through Stochastic Differential Equations
- Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem
- Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
- Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks