Learned reconstruction methods for inverse problems: sample error estimates

• URL: http://arxiv.org/abs/2312.14078v1
• Date: Thu, 21 Dec 2023 17:56:19 GMT
• Title: Learned reconstruction methods for inverse problems: sample error estimates
• Authors: Luca Ratti
• Abstract summary: This dissertation addresses the generalization properties of learned reconstruction methods, and specifically to perform their sample error analysis. A rather general strategy is proposed, whose assumptions are met for a large class of inverse problems and learned methods.
• Score: 0.8702432681310401
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning-based and data-driven techniques have recently become a subject of primary interest in the field of reconstruction and regularization of inverse problems. Besides the development of novel methods, yielding excellent results in several applications, their theoretical investigation has attracted growing interest, e.g., on the topics of reliability, stability, and interpretability. In this work, a general framework is described, allowing us to interpret many of these techniques in the context of statistical learning. This is not intended to provide a complete survey of existing methods, but rather to put them in a working perspective, which naturally allows their theoretical treatment. The main goal of this dissertation is thereby to address the generalization properties of learned reconstruction methods, and specifically to perform their sample error analysis. This task, well-developed in statistical learning, consists in estimating the dependence of the learned operators with respect to the data employed for their training. A rather general strategy is proposed, whose assumptions are met for a large class of inverse problems and learned methods, as depicted via a selection of examples.

Related papers

• Active learning for regression in engineering populations: A risk-informed approach [0.0]
  Regression is a fundamental prediction task common in data-centric engineering applications. Active learning is an approach for preferentially acquiring feature-label pairs in a resource-efficient manner. It is shown that the proposed approach has superior performance in terms of expected cost -- maintaining predictive performance while reducing the number of inspections required.
  arXiv  Detail & Related papers  (2024-09-06T15:03:42Z)
• Learned Regularization for Inverse Problems: Insights from a Spectral Model [1.4963011898406866]
  This chapter provides a theoretically founded investigation of state-of-the-art learning approaches for inverse problems. We give an extended definition of regularization methods and their convergence in terms of the underlying data distributions.
  arXiv  Detail & Related papers  (2023-12-15T14:50:14Z)
• A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning [129.63326990812234]
  We propose a technique named data-dependent contraction to capture how modified losses handle different classes. On top of this technique, a fine-grained generalization bound is established for imbalanced learning, which helps reveal the mystery of re-weighting and logit-adjustment.
  arXiv  Detail & Related papers  (2023-10-07T09:15:08Z)
• Rethinking Generative Methods for Image Restoration in Physics-based Vision: A Theoretical Analysis from the Perspective of Information [19.530052941884996]
  End-to-end generative methods are considered a more promising solution for image restoration in physics-based vision. However, existing generative methods still have plenty of room for improvement in quantitative performance. In this study, we try to re-interpret these generative methods for image restoration tasks using information theory.
  arXiv  Detail & Related papers  (2022-12-05T12:16:27Z)
• Generalization Properties of Retrieval-based Models [50.35325326050263]
  Retrieval-based machine learning methods have enjoyed success on a wide range of problems. Despite growing literature showcasing the promise of these models, the theoretical underpinning for such models remains underexplored. We present a formal treatment of retrieval-based models to characterize their generalization ability.
  arXiv  Detail & Related papers  (2022-10-06T00:33:01Z)
• Latent Properties of Lifelong Learning Systems [59.50307752165016]
  We introduce an algorithm-agnostic explainable surrogate-modeling approach to estimate latent properties of lifelong learning algorithms. We validate the approach for estimating these properties via experiments on synthetic data.
  arXiv  Detail & Related papers  (2022-07-28T20:58:13Z)
• Learned reconstruction with convergence guarantees [3.9402707512848787]
  We will specify relevant notions of convergence for data-driven image reconstruction. An example that is highlighted is the role of ICNN, offering the possibility to combine the power of deep learning with classical convex regularization theory.
  arXiv  Detail & Related papers  (2022-06-11T06:08:25Z)
• A Survey on Deep Semi-supervised Learning [51.26862262550445]
  We first present a taxonomy for deep semi-supervised learning that categorizes existing methods. We then offer a detailed comparison of these methods in terms of the type of losses, contributions, and architecture differences.
  arXiv  Detail & Related papers  (2021-02-28T16:22:58Z)
• Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithms [91.3755431537592]
  We analyze four broad meta-learning strategies which rely on plug-in estimation and pseudo-outcome regression. We highlight how this theoretical reasoning can be used to guide principled algorithm design and translate our analyses into practice.
  arXiv  Detail & Related papers  (2021-01-26T17:11:40Z)
• Accurate and Robust Feature Importance Estimation under Distribution Shifts [49.58991359544005]
  PRoFILE is a novel feature importance estimation method. We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
  arXiv  Detail & Related papers  (2020-09-30T05:29:01Z)
• Joint learning of variational representations and solvers for inverse problems with partially-observed data [13.984814587222811]
  In this paper, we design an end-to-end framework allowing to learn actual variational frameworks for inverse problems in a supervised setting. The variational cost and the gradient-based solver are both stated as neural networks using automatic differentiation for the latter. This leads to a data-driven discovery of variational models.
  arXiv  Detail & Related papers  (2020-06-05T19:53:34Z)

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.