Deep Equilibrium models for Poisson Imaging Inverse problems via Mirror Descent

• URL: http://arxiv.org/abs/2507.11461v1
• Date: Tue, 15 Jul 2025 16:33:01 GMT
• Title: Deep Equilibrium models for Poisson Imaging Inverse problems via Mirror Descent
• Authors: Christian Daniele, Silvia Villa, Samuel Vaiter, Luca Calatroni,
• Abstract summary: Deep Equilibrium Models (DEQs) are implicit neural networks with fixed points.<n>We introduce a novel DEQ formulation based on Mirror Descent defined in terms of a tailored non-Euclidean geometry.<n>We propose computational strategies that enable both efficient training and fully parameter-free inference.
• Score: 7.248102801711294
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep Equilibrium Models (DEQs) are implicit neural networks with fixed points, which have recently gained attention for learning image regularization functionals, particularly in settings involving Gaussian fidelities, where assumptions on the forward operator ensure contractiveness of standard (proximal) Gradient Descent operators. In this work, we extend the application of DEQs to Poisson inverse problems, where the data fidelity term is more appropriately modeled by the Kullback-Leibler divergence. To this end, we introduce a novel DEQ formulation based on Mirror Descent defined in terms of a tailored non-Euclidean geometry that naturally adapts with the structure of the data term. This enables the learning of neural regularizers within a principled training framework. We derive sufficient conditions to guarantee the convergence of the learned reconstruction scheme and propose computational strategies that enable both efficient training and fully parameter-free inference. Numerical experiments show that our method outperforms traditional model-based approaches and it is comparable to the performance of Bregman Plug-and-Play methods, while mitigating their typical drawbacks - namely, sensitivity to initialization and careful tuning of hyperparameters. The code is publicly available at https://github.com/christiandaniele/DEQ-MD.

Related papers

• Preconditioned Inexact Stochastic ADMM for Deep Model [35.37705488695026]
  This paper develops an algorithm, PISA, which enables scalable parallel computing and supports various preconditions.<n>It converges under the sole assumption of Lipschitz continuity of the gradient on a bounded region, removing the need for other conditions commonly imposed by methods.<n>It demonstrates its superior numerical performance compared to various state-of-the-art iterations.
  arXiv  Detail & Related papers  (2025-02-15T12:28:51Z)
• Nonparametric Filtering, Estimation and Classification using Neural Jump ODEs [3.437372707846067]
  Neural Jump ODEs model the conditional expectation between observations by neural ODEs and jump at arrival of new observations.<n>They have demonstrated effectiveness for fully data-driven online forecasting in settings with irregular and partial observations.<n>This work extends the framework to input-output systems, enabling direct applications in online filtering and classification.
  arXiv  Detail & Related papers  (2024-12-04T12:31:15Z)
• Sparse Bayesian Generative Modeling for Compressive Sensing [8.666730973498625]
  This work addresses the fundamental linear inverse problem in compressive sensing (CS) by introducing a new type of regularizing generative prior. We support our approach theoretically through the concept of variational inference and validate it empirically using different types of compressible signals.
  arXiv  Detail & Related papers  (2024-11-14T14:37:47Z)
• Scaling and renormalization in high-dimensional regression [72.59731158970894]
  We present a unifying perspective on recent results on ridge regression.<n>We use the basic tools of random matrix theory and free probability, aimed at readers with backgrounds in physics and deep learning.<n>Our results extend and provide a unifying perspective on earlier models of scaling laws.
  arXiv  Detail & Related papers  (2024-05-01T15:59:00Z)
• Deep Horseshoe Gaussian Processes [0.0]
  We introduce the deep Horseshoe Gaussian process Deep-HGP, a new simple prior based on deep Gaussian processes with a squared-exponential kernel.<n>For nonparametric regression with random design, we show that the associated posterior distribution recovers the unknown true regression curve in terms of quadratic loss.<n>The convergence rates are simultaneously adaptive to both the smoothness of the regression function and to its structure in terms of compositions.
  arXiv  Detail & Related papers  (2024-03-04T05:30:43Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Function-Space Regularization in Neural Networks: A Probabilistic Perspective [51.133793272222874]
  We show that we can derive a well-motivated regularization technique that allows explicitly encoding information about desired predictive functions into neural network training. We evaluate the utility of this regularization technique empirically and demonstrate that the proposed method leads to near-perfect semantic shift detection and highly-calibrated predictive uncertainty estimates.
  arXiv  Detail & Related papers  (2023-12-28T17:50:56Z)
• A PAC-Bayesian Perspective on the Interpolating Information Criterion [54.548058449535155]
  We show how a PAC-Bayes bound is obtained for a general class of models, characterizing factors which influence performance in the interpolating regime. We quantify how the test error for overparameterized models achieving effectively zero training error depends on the quality of the implicit regularization imposed by e.g. the combination of model, parameter-initialization scheme.
  arXiv  Detail & Related papers  (2023-11-13T01:48:08Z)
• A Deep Unrolling Model with Hybrid Optimization Structure for Hyperspectral Image Deconvolution [50.13564338607482]
  We propose a novel optimization framework for the hyperspectral deconvolution problem, called DeepMix.<n>It consists of three distinct modules, namely, a data consistency module, a module that enforces the effect of the handcrafted regularizers, and a denoising module.<n>This work proposes a context aware denoising module designed to sustain the advancements achieved by the cooperative efforts of the other modules.
  arXiv  Detail & Related papers  (2023-06-10T08:25:16Z)
• Koopman Kernel Regression [6.116741319526748]
  We show that Koopman operator theory offers a beneficial paradigm for characterizing forecasts via linear time-invariant (LTI) ODEs. We derive a universal Koopman-invariant kernel reproducing Hilbert space (RKHS) that solely spans transformations into LTI dynamical systems. Our experiments demonstrate superior forecasting performance compared to Koopman operator and sequential data predictors.
  arXiv  Detail & Related papers  (2023-05-25T16:22:22Z)
• Robust Implicit Networks via Non-Euclidean Contractions [63.91638306025768]
  Implicit neural networks show improved accuracy and significant reduction in memory consumption. They can suffer from ill-posedness and convergence instability. This paper provides a new framework to design well-posed and robust implicit neural networks.
  arXiv  Detail & Related papers  (2021-06-06T18:05:02Z)
• Leveraging Global Parameters for Flow-based Neural Posterior Estimation [90.21090932619695]
  Inferring the parameters of a model based on experimental observations is central to the scientific method. A particularly challenging setting is when the model is strongly indeterminate, i.e., when distinct sets of parameters yield identical observations. We present a method for cracking such indeterminacy by exploiting additional information conveyed by an auxiliary set of observations sharing global parameters.
  arXiv  Detail & Related papers  (2021-02-12T12:23:13Z)

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.