Latent Generative Models with Tunable Complexity for Compressed Sensing and other Inverse Problems

• URL: http://arxiv.org/abs/2603.07357v2
• Date: Tue, 10 Mar 2026 13:28:54 GMT
• Title: Latent Generative Models with Tunable Complexity for Compressed Sensing and other Inverse Problems
• Abstract summary: We develop tunable-complexity priors for solving inverse problems.<n>We show empirically that tunable priors consistently achieve lower reconstruction errors than fixed-complexity baselines.<n>This work demonstrates the potential of tunable-complexity generative priors and motivates both the development of supporting theory and their application across a wide range of inverse problems.
• Score: 7.111209122554222
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative models have emerged as powerful priors for solving inverse problems. These models typically represent a class of natural signals using a single fixed complexity or dimensionality. This can be limiting: depending on the problem, a fixed complexity may result in high representation error if too small, or overfitting to noise if too large. We develop tunable-complexity priors for diffusion models, normalizing flows, and variational autoencoders, leveraging nested dropout. Across tasks including compressed sensing, inpainting, denoising, and phase retrieval, we show empirically that tunable priors consistently achieve lower reconstruction errors than fixed-complexity baselines. In the linear denoising setting, we provide a theoretical analysis that explicitly characterizes how the optimal tuning parameter depends on noise and model structure. This work demonstrates the potential of tunable-complexity generative priors and motivates both the development of supporting theory and their application across a wide range of inverse problems.

Related papers

• Full-Model Optimality for Tunable Linear Generative Priors in Compressed Sensing [2.0737159978603925]
  We establish theory for compressed sensing in the setting of a tunable family of linear generative priors.<n>We prove that in noiseless compressed sensing, the full-dimensional linear prior attains the minimum expected reconstruction error.<n>This result indicates that the experimental benefits of tunability in compressed sensing with neural network priors arises due to nonlinearities in the generative models.
  arXiv  Detail & Related papers  (2026-09-02T16:22:26Z)
• Learning to Pose Problems: Reasoning-Driven and Solver-Adaptive Data Synthesis for Large Reasoning Models [54.29243291958429]
  We develop a problem generator that reasons explicitly to plan problem directions before synthesis.<n>We treat the solver's feedback on synthetic problems as a reward signal, enabling the generator to calibrate difficulty.<n>Our method achieves an average improvement of 2.5% and generalizes to both language and vision-language models.
  arXiv  Detail & Related papers  (2025-11-13T03:08:51Z)
• Noise is All You Need: Solving Linear Inverse Problems by Noise Combination Sampling with Diffusion Models [7.219077740523681]
  We propose a novel method that synthesizes an optimal noise vector from a noise subspace to approximate the measurement score.<n>Our method can be applied to a wide range of inverse problem solvers, including image compression.
  arXiv  Detail & Related papers  (2025-10-24T07:46:23Z)
• Inverse Flow and Consistency Models [5.1438052682409605]
  Inverse Flow (IF) is a novel framework that enables using generative models for inverse generation problems.<n>IF can be flexibly applied to nearly any continuous noise distribution and allows complex dependencies.<n>We demonstrate the effectiveness of IF on synthetic and real datasets, outperforming prior approaches.
  arXiv  Detail & Related papers  (2025-02-17T01:11:42Z)
• Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency [7.671153315762146]
  Training diffusion models in the pixel space are both data-intensive and computationally demanding. Latent diffusion models, which operate in a much lower-dimensional space, offer a solution to these challenges. We propose textitReSample, an algorithm that can solve general inverse problems with pre-trained latent diffusion models.
  arXiv  Detail & Related papers  (2023-07-16T18:42:01Z)
• A Variational Perspective on Solving Inverse Problems with Diffusion Models [101.831766524264]
  Inverse tasks can be formulated as inferring a posterior distribution over data. This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable. We propose a variational approach that by design seeks to approximate the true posterior distribution.
  arXiv  Detail & Related papers  (2023-05-07T23:00:47Z)
• DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion [66.21290235237808]
  We introduce an energy constrained diffusion model which encodes a batch of instances from a dataset into evolutionary states. We provide rigorous theory that implies closed-form optimal estimates for the pairwise diffusion strength among arbitrary instance pairs. Experiments highlight the wide applicability of our model as a general-purpose encoder backbone with superior performance in various tasks.
  arXiv  Detail & Related papers  (2023-01-23T15:18:54Z)
• Removing Structured Noise with Diffusion Models [13.50969999636388]
  We show that the powerful paradigm of posterior sampling with diffusion models can be extended to include rich, structured, noise models.<n>We demonstrate strong performance gains across various inverse problems with structured noise, outperforming competitive baselines.<n>This opens up new opportunities and relevant practical applications of diffusion modeling for inverse problems in the context of non-Gaussian measurement models.
  arXiv  Detail & Related papers  (2023-01-20T23:42:25Z)
• Diffusion Posterior Sampling for General Noisy Inverse Problems [50.873313752797124]
  We extend diffusion solvers to handle noisy (non)linear inverse problems via approximation of the posterior sampling. Our method demonstrates that diffusion models can incorporate various measurement noise statistics.
  arXiv  Detail & Related papers  (2022-09-29T11:12:27Z)
• A Variational Inference Approach to Inverse Problems with Gamma Hyperpriors [60.489902135153415]
  This paper introduces a variational iterative alternating scheme for hierarchical inverse problems with gamma hyperpriors. The proposed variational inference approach yields accurate reconstruction, provides meaningful uncertainty quantification, and is easy to implement.
  arXiv  Detail & Related papers  (2021-11-26T06:33:29Z)
• Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness [68.97830259849086]
  Most datasets only capture a simpler subproblem and likely suffer from spurious features. We study adversarial robustness - a local generalization property - to reveal hard, model-specific instances and spurious features. Unlike in other applications, where perturbation models are designed around subjective notions of imperceptibility, our perturbation models are efficient and sound. Surprisingly, with such perturbations, a sufficiently expressive neural solver does not suffer from the limitations of the accuracy-robustness trade-off common in supervised learning.
  arXiv  Detail & Related papers  (2021-10-21T07:28:11Z)
• Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition [34.235007566913396]
  We describe an interpretable, symmetric decomposition of the variance into terms associated with the labels. We find that the bias decreases monotonically with the network width, but the variance terms exhibit non-monotonic behavior. We also analyze the strikingly rich phenomenology that arises.
  arXiv  Detail & Related papers  (2020-11-04T21:04:02Z)

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.