mlsanityData to 7 Oct 2026

CQnet: convex-geometric interpretation and constraining neural-network trajectories

arXiv 2302.10895 ↗First posted 9 Feb 2023cs.LG cs.AI math.OCcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce CQnet, a neural network with origins in the CQ algorithm for solving convex split-feasibility problems and forward-backward splitting. CQnet's trajectories are interpretable as particles that are tracking a changing constraint set via its point-to-set distance function while being elements of another constraint set at every layer. More than just a convex-geometric interpretation, CQnet accommodates learned and deterministic constraints that may be sample or data-specific and are satisfied by every layer and the output. Furthermore, the states in CQnet progress toward another constraint set at every layer. We provide proof of stability/nonexpansiveness with minimal assumptions. The combination of constraint handling and stability put forward CQnet as a candidate for various tasks where prior knowledge exists on the network states or output.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 71 references that are in the map. First posted on arXiv 9 Feb 2023.

Builds on

40 of 71 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2019Deep Equilibrium Modelscited by 603
  6. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 588
  7. 2019Differentiable Convex Optimization Layerscited by 458
  8. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
  9. 2017Stable Architectures for Deep Neural Networkscited by 340
  10. 2019Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networkscited by 290
  11. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
  12. 2018Safe Exploration in Continuous Action Spacescited by 237
28 more
  1. 2018Sorting out Lipschitz function approximationcited by 211
  2. 2017Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equationscited by 203
  3. 2018Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networkscited by 193
  4. 2015Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentationcited by 189
  5. 2018Deep Neural Networks Motivated by Partial Differential Equationscited by 187
  6. 2019Implicit Deep Learningcited by 124
  7. 2015Constrained Convolutional Neural Networks for Weakly Supervised Segmentationcited by 100
  8. 2020Monotone operator equilibrium networkscited by 100
  9. 2018The Singular Values of Convolutional Layerscited by 95
  10. 2016Label-Free Supervision of Neural Networks with Physics and Domain Knowledgecited by 74
  11. 2017Reversible Architectures for Arbitrarily Deep Residual Neural Networkscited by 69
  12. 2018Constrained-CNN losses for weakly supervised segmentationcited by 62
  13. 2019Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operatorscited by 54
  14. 2019The Geometry of Deep Networks: Power Diagram Subdivisioncited by 53
  15. 2016Convolutional Neural Networks Analyzed via Convolutional Sparse Codingcited by 51
  16. 2022Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagationcited by 45
  17. 2017Imposing Hard Constraints on Deep Networks: Promises and Limitationscited by 42
  18. 2020Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervisioncited by 40
  19. 2018Deep Neural Network Structures Solving Variational Inequalitiescited by 25
  20. 2018Deep Unfolding of a Proximal Interior Point Method for Image Restorationcited by 23
  21. 2018On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networkscited by 20
  22. 2021A Neural Network Approach for High-Dimensional Optimal Control Applied to Multi-Agent Path Findingcited by 18
  23. 2021Feasibility-based Fixed Point Networkscited by 17
  24. 2019Learned imaging with constraints and uncertainty quantificationcited by 8
  25. 2020Sample-Specific Output Constraints for Neural Networkscited by 7
  26. 2016Some Insights into the Geometry and Training of Neural Networkscited by 2
  27. 2019Dynamic string-averaging CQ-methods for the split feasibility problem with percentage violation constraints arising in radiation therapy treatment planningcited by 2
  28. 2022Neural DAEs: Constrained neural networkscited by 1

Built on by

Not cited yet.