Inverse Problems, Deep Learning, and Symmetry Breaking

• URL: http://arxiv.org/abs/2003.09077v1
• Date: Fri, 20 Mar 2020 02:43:57 GMT
• Title: Inverse Problems, Deep Learning, and Symmetry Breaking
• Authors: Kshitij Tayal, Chieh-Hsin Lai, Vipin Kumar, Ju Sun
• Abstract summary: In many physical systems, inputs related by intrinsic system symmetries are mapped to the same output. We show that careful symmetry breaking on the training data can help get rid of the difficulties and significantly improve the learning performance.
• Score: 6.54545059421233
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In many physical systems, inputs related by intrinsic system symmetries are mapped to the same output. When inverting such systems, i.e., solving the associated inverse problems, there is no unique solution. This causes fundamental difficulties for deploying the emerging end-to-end deep learning approach. Using the generalized phase retrieval problem as an illustrative example, we show that careful symmetry breaking on the training data can help get rid of the difficulties and significantly improve the learning performance. We also extract and highlight the underlying mathematical principle of the proposed solution, which is directly applicable to other inverse problems.

Related papers

• Paired Autoencoders for Inverse Problems [3.355436702348694]
  We consider the solution of nonlinear inverse problems where the forward problem is a discretization of a partial differential equation. The main computational bottleneck of typical algorithms is the direct estimation of the data misfit. We use a paired autoencoder framework as a likelihood-free estimator for inverse problems.
  arXiv  Detail & Related papers  (2024-05-21T22:00:34Z)
• What is Wrong with End-to-End Learning for Phase Retrieval? [6.464093417537727]
  We show how symmetries in the forward model can cause learning difficulties when data-driven deep learning approaches are used to solve such problems. We show how to overcome them by preprocessing the training set before any learning, i.e., symmetry breaking.
  arXiv  Detail & Related papers  (2024-03-18T03:01:53Z)
• Reverse em-problem based on Bregman divergence and its application to classical and quantum information theory [53.64687146666141]
  Recent paper introduced an analytical method for calculating the channel capacity without the need for iteration. We turn our attention to the reverse em-problem, proposed by Toyota. We derive a non-iterative formula for the reverse em-problem.
  arXiv  Detail & Related papers  (2024-03-14T10:20:28Z)
• Exploring the solution space of linear inverse problems with GAN latent geometry [23.779985842891705]
  Inverse problems consist in reconstructing signals from incomplete sets of measurements. We propose a method to generate multiple reconstructions that fit both the measurements and a data-driven prior learned by a generative adversarial network.
  arXiv  Detail & Related papers  (2022-07-01T14:33:44Z)
• 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)
• Conditional physics informed neural networks [85.48030573849712]
  We introduce conditional PINNs (physics informed neural networks) for estimating the solution of classes of eigenvalue problems. We show that a single deep neural network can learn the solution of partial differential equations for an entire class of problems.
  arXiv  Detail & Related papers  (2021-04-06T18:29:14Z)
• Consistency analysis of bilevel data-driven learning in inverse problems [1.0705399532413618]
  We consider the adaptive learning of the regularization parameter from data by means of optimization. We demonstrate how to implement our framework on linear inverse problems. Online numerical schemes are derived using the gradient descent method.
  arXiv  Detail & Related papers  (2020-07-06T12:23:29Z)
• Total Deep Variation: A Stable Regularizer for Inverse Problems [71.90933869570914]
  We introduce the data-driven general-purpose total deep variation regularizer. In its core, a convolutional neural network extracts local features on multiple scales and in successive blocks. We achieve state-of-the-art results for numerous imaging tasks.
  arXiv  Detail & Related papers  (2020-06-15T21:54:15Z)
• Regularization of Inverse Problems by Neural Networks [0.0]
  Inverse problems arise in a variety of imaging applications including computed tomography, non-destructive testing, and remote sensing. The characteristic features of inverse problems are the non-uniqueness and instability of their solutions. Deep learning techniques and neural networks demonstrated to significantly outperform classical solution methods for inverse problems.
  arXiv  Detail & Related papers  (2020-06-06T20:49:12Z)
• Solving Inverse Problems with a Flow-based Noise Model [100.18560761392692]
  We study image inverse problems with a normalizing flow prior. Our formulation views the solution as the maximum a posteriori estimate of the image conditioned on the measurements. We empirically validate the efficacy of our method on various inverse problems, including compressed sensing with quantized measurements and denoising with highly structured noise patterns.
  arXiv  Detail & Related papers  (2020-03-18T08:33:49Z)
• 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.