mlsanityData to 14 Oct 2026

Prior-aware and Context-guided Group Sampling for Active Probabilistic Subsampling

arXiv 2607.07083 ↗First posted 8 Jul 2026eess.SY cs.LG cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

Subsampling significantly reduces the number of measurements, thereby streamlining data processing and transfer overhead, and shortening acquisition time across diverse real-world applications. The recently introduced Active Deep Probabilistic Subsampling (A-DPS) approach jointly optimizes both the subsampling pattern and the downstream task model, enabling instance- and subject-specific sampling trajectories and effective adaptation to new data at inference time. However, this approach does not fully leverage valuable dataset priors and relies on top-1 sampling, which can impede the optimization process. Herein, we enhance A-DPS by integrating a deterministic (fixed) prior-informed sampling pattern derived from the training dataset, along with group-based sampling via top-k sampling, to achieve more robust optimization, method we call Prior-aware and context-guided Group-based Active DPS (PGA-DPS). We also provide a theoretical analysis supporting improved optimization via group sampling, and validate this with empirical results. We evaluated PGA-DPS on three tasks: classification, image reconstruction, and segmentation, using the MNIST, CIFAR-10, fastMRI knee, and hyperspectral AeroRIT datasets, respectively. In every case, PGA-DPS outperformed A-DPS, DPS, and all other sampling methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 60 references that are in the map. First posted on arXiv 8 Jul 2026.

Builds on

35 of 60 references.

References · 35

  1. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  2. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  3. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  4. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  5. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 470
  6. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 415
  7. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
  8. 2018How Does Batch Normalization Help Optimization?cited by 357
  9. 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 314
  10. 2019Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacementcited by 211
  11. 2014A* Samplingcited by 151
  12. 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 145
23 more
  1. 2018Neural Nearest Neighbors Networkscited by 98
  2. 2020Lipschitz constant estimation of Neural Networks via sparse polynomial optimizationcited by 87
  3. 2022Learning Smooth Neural Functions via Lipschitz Regularizationcited by 86
  4. 2017REBAR: Low-variance, unbiased gradient estimates for discrete latent variable modelscited by 79
  5. 2019Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisitioncited by 56
  6. 2018Neural Proximal Gradient Descent for Compressive Imagingcited by 46
  7. 2020Active MR k-space Sampling with Reinforcement Learningcited by 46
  8. 2022Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagationcited by 45
  9. 2020Experimental design for MRI by greedy policy searchcited by 40
  10. 2019Self-Supervised Deep Active Accelerated MRIcited by 24
  11. 2016Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysiscited by 22
  12. 2020Extending LOUPE for K-space Under-sampling Pattern Optimization in Multi-coil MRIcited by 22
  13. 2019Learning the Sampling Pattern for MRIcited by 21
  14. 2018Representing smooth functions as compositions of near-identity functions with implications for deep network optimizationcited by 15
  15. 2019Joint learning of cartesian undersampling and reconstruction for accelerated MRIcited by 14
  16. 2019Learning Sub-Sampling and Signal Recovery with Applications in Ultrasound Imagingcited by 13
  17. 2020Learning to Scan: A Deep Reinforcement Learning Approach for Personalized Scanning in CT Imagingcited by 13
  18. 2021Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classificationcited by 12
  19. 2019AeroRIT: A New Scene for Hyperspectral Image Analysiscited by 10
  20. 2019Scalable Learning-Based Sampling Optimization for Compressive Dynamic MRIcited by 9
  21. 2022SRL-SOA: Self-Representation Learning with Sparse 1D-Operational Autoencoder for Hyperspectral Image Band Selectioncited by 4
  22. 2024Learning Task-Specific Sampling Strategy for Sparse-View CT Reconstructioncited by 1
  23. 2025Sampling Innovation-Based Adaptive Compressive Sensingcited by 1

Built on by

Not cited yet.