Learned iterative networks: An operator learning perspective

• URL: http://arxiv.org/abs/2512.08444v1
• Date: Tue, 09 Dec 2025 10:18:51 GMT
• Title: Learned iterative networks: An operator learning perspective
• Authors: Andreas Hauptmann, Ozan Öktem,
• Abstract summary: We present a unified operator view for learned iterative networks.<n>Specifically, we formulate a learned reconstruction operator, defining how to compute, and separately the learning problem, which defines what to compute.<n>In this setting we present common approaches and show that many approaches are closely related in their core.
• Score: 3.8559042217241566
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learned image reconstruction has become a pillar in computational imaging and inverse problems. Among the most successful approaches are learned iterative networks, which are formulated by unrolling classical iterative optimisation algorithms for solving variational problems. While the underlying algorithm is usually formulated in the functional analytic setting, learned approaches are often viewed as purely discrete. In this chapter we present a unified operator view for learned iterative networks. Specifically, we formulate a learned reconstruction operator, defining how to compute, and separately the learning problem, which defines what to compute. In this setting we present common approaches and show that many approaches are closely related in their core. We review linear as well as nonlinear inverse problems in this framework and present a short numerical study to conclude.

Related papers

• Fast algorithms enabling optimization and deep learning for photoacoustic tomography in a circular detection geometry [2.5387090319723717]
  inverse source problem arising in photoacoustic tomography and in several other coupled-physics modalities is frequently solved by iterative algorithms.<n>New algorithms for numerical evaluation of the forward and adjoint operators are presented.<n>A Python implementation of our algorithms and computational examples are available to the general public.
  arXiv  Detail & Related papers  (2025-10-28T17:49:31Z)
• Operator learning meets inverse problems: A probabilistic perspective [5.311997112925023]
  Operator learning offers a robust framework for approximating mappings between infinite-dimensional function spaces.<n>This chapter surveys developments at the intersection of operator learning and inverse problems.
  arXiv  Detail & Related papers  (2025-08-27T18:34:40Z)
• A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms [64.3064050603721]
  We generalize Runge-Kutta neural network to a recurrent neural network (R2N2) superstructure for the design of customized iterative algorithms. We demonstrate that regular training of the weight parameters inside the proposed superstructure on input/output data of various computational problem classes yields similar iterations to Krylov solvers for linear equation systems, Newton-Krylov solvers for nonlinear equation systems, and Runge-Kutta solvers for ordinary differential equations.
  arXiv  Detail & Related papers  (2022-11-22T16:30:33Z)
• Invariant Causal Mechanisms through Distribution Matching [86.07327840293894]
  In this work we provide a causal perspective and a new algorithm for learning invariant representations. Empirically we show that this algorithm works well on a diverse set of tasks and in particular we observe state-of-the-art performance on domain generalization.
  arXiv  Detail & Related papers  (2022-06-23T12:06:54Z)
• Learning Non-Vacuous Generalization Bounds from Optimization [8.294831479902658]
  We present a simple yet non-vacuous generalization bound from the optimization perspective. We achieve this goal by leveraging that the hypothesis set accessed by gradient algorithms is essentially fractal-like. Numerical studies demonstrate that our approach is able to yield plausible generalization guarantees for modern neural networks.
  arXiv  Detail & Related papers  (2022-06-09T08:59:46Z)
• Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning [53.17258888552998]
  This work proposes an exploration variant of the basic $Q$-learning protocol with linear function approximation. We show that the performance of the algorithm degrades very gracefully under a novel and more permissive notion of approximation error.
  arXiv  Detail & Related papers  (2022-06-01T23:26:51Z)
• Provably Convergent Algorithms for Solving Inverse Problems Using Generative Models [47.208080968675574]
  We study the use of generative models in inverse problems with more complete understanding. We support our claims with experimental results for solving various inverse problems. We propose an extension of our approach that can handle model mismatch (i.e., situations where the generative prior is not exactly applicable)
  arXiv  Detail & Related papers  (2021-05-13T15:58:27Z)
• Model-Aware Regularization For Learning Approaches To Inverse Problems [11.314492463814817]
  We provide an analysis of the generalisation error of deep learning methods applicable to inverse problems. We propose a 'plug-and-play' regulariser that leverages the knowledge of the forward map to improve the generalization of the network. We demonstrate the efficacy of our model-aware regularised deep learning algorithms against other state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-06-18T21:59:03Z)
• Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems [107.3868459697569]
  We introduce an eigendecomposition-free approach to training a deep network. We show that our approach is much more robust than explicit differentiation of the eigendecomposition. Our method has better convergence properties and yields state-of-the-art results.
  arXiv  Detail & Related papers  (2020-04-15T04:29:34Z)
• Total Deep Variation for Linear Inverse Problems [71.90933869570914]
  We propose a novel learnable general-purpose regularizer exploiting recent architectural design patterns from deep learning. We show state-of-the-art performance for classical image restoration and medical image reconstruction problems.
  arXiv  Detail & Related papers  (2020-01-14T19:01:50Z)

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.