Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees

• URL: http://arxiv.org/abs/2605.05387v1
• Date: Wed, 06 May 2026 19:19:54 GMT
• Title: Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees
• Abstract summary: We study zero-shot conditional sampling with pretrained diffusion models for linear inverse problems.<n>We prove that the error from replacing this score by the unconditional tangent score is upper bounded by a dimension-free conditional mutual information between observed and unobserved components.
• Score: 10.73598638822051
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study zero-shot conditional sampling with pretrained diffusion models for linear inverse problems, including inpainting and super-resolution. In these problems, the observation determines only part of the unknown signal. The remaining degrees of freedom must be sampled according to the correct conditional data distribution. Existing projection-based samplers enforce measurement consistency by correcting the observed component during reverse diffusion. However, measurement consistency alone does not determine how probability mass should be distributed along the feasible set, and this can lead to biased conditional samples. We analyze this issue through a normal--tangent decomposition of the score function. For Gaussian noising, the observed-direction score is exactly determined by the measurement; only the tangent conditional score is unknown. We prove that the error from replacing this score by the unconditional tangent score is upper bounded by a dimension-free conditional mutual information between observed and unobserved components. This gives an information-theoretic decomposition into initialization and pathwise score-mismatch errors. Motivated by the theory, we propose a projected-Langevin initialization followed by guided reverse denoising, which outperforms a strong projection-based baseline in inpainting and super-resolution experiments.

Related papers

• The Loss Floor of Denoising Score Matching: Fisher Geometry from Schrödinger Bridges [4.661816556403101]
  We show that for a general corruption kernel under mild regularity assumptions, it is exactly the trace of the Fisher--Rao metric of the conditional endpoint family.<n>We derive the result from a Schr"odinger bridge variational principle, in which the ideal objective arises as excess path-space relative entropy.
  arXiv  Detail & Related papers  (2026-08-24T23:48:06Z)
• Posterior Information Dynamics of Diffusion Models for Linear Inverse Problems [11.548853370822343]
  We study the process through the smoothed likelihood force, the difference between exact posterior and prior scores at each noise level.<n>Averaging over measurements yields an information--minimum mean-square error (I-MMSE) identity linking information gain to denoising-error reduction.
  arXiv  Detail & Related papers  (2026-08-22T00:53:42Z)
• Should the Boundary Term Be Learned in Reflected Diffusion? Conormal Trace and Reflection Masking [4.262498901922258]
  We study score learning for reflected diffusion on bounded domains.<n>We identify reflection masking: hard reflection can keep samples feasible even when the learned trace is wrong.
  arXiv  Detail & Related papers  (2026-08-04T11:05:02Z)
• Rethinking Structural Anomaly Detection: From Decision Boundaries to Projection Operators [51.771100367755544]
  We introduce a geometric perspective to address the mismatch between the inductive bias of existing methods and the structure of the data.<n>Specifically, we learn a projection operator onto the manifold of normal samples and define a sample as anomalous if it is altered by this projection.<n> Notably, it provides a unifying interpretation of reconstruction-based methods by explaining their success and failure in terms of projection quality.
  arXiv  Detail & Related papers  (2026-06-13T12:37:20Z)
• The conditional-mean barrier: From deterministic regression to conditional distribution learning [6.160113667162026]
  This tutorial develops a self-contained module centered on the conditional-mean barrier.<n>Adding latent randomness to a squared-loss predictor collapses it back to the conditional mean.<n>We briefly organize common distributional objectives, including negative log-likelihood, moment and observable matching, variational objectives, adversarial divergences, and score matching.
  arXiv  Detail & Related papers  (2026-05-27T07:31:42Z)
• Diffusion-Based Posterior Sampling: A Feynman-Kac Analysis of Bias and Stability [13.640937605089865]
  Diffusion-based posterior samplers use pretrained diffusion priors to sample from measurement- or reward-conditioned posteriors.<n>This paper introduces a tractable surrogate path connecting the true posterior to a standard Gaussian and comparing it to the sampler's path.<n>A Feynman-Kac representation then expresses the Radon-Nikodym correction as an explicit path expectation, identifying which posterior regions are over- or under-sampled.
  arXiv  Detail & Related papers  (2026-05-07T16:37:29Z)
• Solving physics-constrained inverse problems with conditional flow matching [0.6567875008573567]
  We present a conditional flow matching framework for solving physics-constrained inverse problems.<n>A neural network is trained to learn the velocity field of a probability flow ordinary differential equation.<n>We show that overtraining can induce behavior in the generated conditional distributions.
  arXiv  Detail & Related papers  (2026-03-14T21:43:48Z)
• DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment [92.70019102733453]
  Training time-series forecast models requires aligning the conditional distribution of model forecasts with that of the label sequence.<n>We propose DistDF, which achieves alignment by alternatively minimizing a discrepancy between the conditional forecast and label distributions.
  arXiv  Detail & Related papers  (2025-10-28T16:09:59Z)
• On the Wasserstein Convergence and Straightness of Rectified Flow [54.580605276017096]
  Rectified Flow (RF) is a generative model that aims to learn straight flow trajectories from noise to data.<n>We provide a theoretical analysis of the Wasserstein distance between the sampling distribution of RF and the target distribution.<n>We present general conditions guaranteeing uniqueness and straightness of 1-RF, which is in line with previous empirical findings.
  arXiv  Detail & Related papers  (2024-10-19T02:36:11Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• The Implicit Delta Method [61.36121543728134]
  In this paper, we propose an alternative, the implicit delta method, which works by infinitesimally regularizing the training loss of uncertainty. We show that the change in the evaluation due to regularization is consistent for the variance of the evaluation estimator, even when the infinitesimal change is approximated by a finite difference.
  arXiv  Detail & Related papers  (2022-11-11T19:34:17Z)
• Composing Normalizing Flows for Inverse Problems [89.06155049265641]
  We propose a framework for approximate inference that estimates the target conditional as a composition of two flow models. Our method is evaluated on a variety of inverse problems and is shown to produce high-quality samples with uncertainty.
  arXiv  Detail & Related papers  (2020-02-26T19:01:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.