mlsanityData to 7 Oct 2026

Gradient-Based Learning of Discrete Structured Measurement Operators for Signal Recovery

arXiv 2202.03391 ↗First posted 7 Feb 2022cs.LG eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

Countless signal processing applications include the reconstruction of signals from few indirect linear measurements. The design of effective measurement operators is typically constrained by the underlying hardware and physics, posing a challenging and often even discrete optimization task. While the potential of gradient-based learning via the unrolling of iterative recovery algorithms has been demonstrated, it has remained unclear how to leverage this technique when the set of admissible measurement operators is structured and discrete. We tackle this problem by combining unrolled optimization with Gumbel reparametrizations, which enable the computation of low-variance gradient estimates of categorical random variables. Our approach is formalized by GLODISMO (Gradient-based Learning of DIscrete Structured Measurement Operators). This novel method is easy-to-implement, computationally efficient, and extendable due to its compatibility with automatic differentiation. We empirically demonstrate the performance and flexibility of GLODISMO in several prototypical signal recovery applications, verifying that the learned measurement matrices outperform conventional designs based on randomization as well as discrete optimization baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 71 references that are in the map. First posted on arXiv 7 Feb 2022.

Builds on

22 of 71 references.

References · 22

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  5. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  6. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  7. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
  8. 2018SNAS: Stochastic Neural Architecture Searchcited by 288
  9. 2014A* Samplingcited by 150
  10. 2014Neural Variational Inference and Learning in Belief Networkscited by 116
  11. 2018Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholdscited by 83
  12. 2020Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challengecited by 59
10 more
  1. 2020Solving Inverse Problems With Deep Neural Networks -- Robustness Included?cited by 58
  2. 2016GANS for Sequences of Discrete Elements with the Gumbel-softmax Distributioncited by 47
  3. 2019Learning-based Optimization of the Under-sampling Pattern in MRIcited by 32
  4. 2018Learning a Compressed Sensing Measurement Matrix via Gradient Unrollingcited by 16
  5. 2020Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstructioncited by 14
  6. 2020Learning Sampling and Model-Based Signal Recovery for Compressed Sensing MRIcited by 9
  7. 2016Compressed Learning: A Deep Neural Network Approachcited by 8
  8. 2020Neurally Augmented ALISTAcited by 5
  9. 2020Plug-And-Play Learned Gaussian-mixture Approximate Message Passingcited by 3
  10. 2019Deep-learning-based Optimization of the Under-sampling Pattern in MRIcited by 2

Built on by

Not cited yet.