mlsanityData to 14 Oct 2026

TropNNC: Structured Neural Network Compression Using Tropical Geometry

arXiv 2409.03945 ↗First posted 5 Sep 2024cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We present TropNNC, a framework for compressing neural networks with linear and convolutional layers and ReLU-type activations using tropical geometry. By representing a network's output as a tropical rational function, TropNNC enables structured compression via reduction of the corresponding tropical polynomials. Our method identifies redundancy via similarity and improves upon the geometric approximation of previous work by adaptively selecting the weights of retained neurons. We relate it to SVD and spectral clustering, and provide insights into network compression beyond the specific setting considered. We provide the tightest known theoretical compression bound, and the first successful application of tropical geometry to convolutional layers. TropNNC requires access only to network weights - no training data - and achieves competitive performance on MNIST, CIFAR, and ImageNet, matching strong baselines such as ThiNet and CUP.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 43 of its 79 references that are in the map. First posted on arXiv 5 Sep 2024.

Builds on

43 of 79 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2018Neural Ordinary Differential Equationscited by 3,779
  4. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  5. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  6. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  7. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 950
  8. 2020What is the State of Neural Network Pruning?cited by 583
  9. 2016Learning Structured Sparsity in Deep Neural Networkscited by 541
  10. 2019Object Detection in 20 Years: A Surveycited by 531
  11. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 442
  12. 2014On the Number of Linear Regions of Deep Neural Networkscited by 381
31 more
  1. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 367
  2. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  3. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 306
  4. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 292
  5. 2018Model compression via distillation and quantizationcited by 289
  6. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 284
  7. 2017NISP: Pruning Networks using Neuron Importance Score Propagationcited by 228
  8. 2013Predicting Parameters in Deep Learningcited by 224
  9. 2015Quantized Convolutional Neural Networks for Mobile Devicescited by 215
  10. 2018A Comprehensive Survey of Deep Learning for Image Captioningcited by 214
  11. 2014Compressing Deep Convolutional Networks using Vector Quantizationcited by 195
  12. 2023From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inferencecited by 170
  13. 2015Compressing Neural Networks with the Hashing Trickcited by 150
  14. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  15. 2015Convolutional neural networks with low-rank regularizationcited by 103
  16. 2018Tropical Geometry of Deep Neural Networkscited by 95
  17. 2021CHIP: CHannel Independence-based Pruning for Compact Neural Networkscited by 78
  18. 2021Convolutional Neural Network Pruning with Structural Redundancy Reductioncited by 73
  19. 2017Adaptive Quantization for Deep Neural Networkcited by 67
  20. 2019Neural Network Pruning with Residual-Connections and Limited-Datacited by 52
  21. 2015Structured Transforms for Small-Footprint Deep Learningcited by 42
  22. 2018GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinkingcited by 32
  23. 2023QuantEase: Optimization-based Quantization for Language Modelscited by 29
  24. 2018A Tropical Approach to Neural Networks with Piecewise Linear Activationscited by 26
  25. 2015Training CNNs with Low-Rank Filters for Efficient Image Classificationcited by 25
  26. 2020On the Decision Boundaries of Neural Networks: A Tropical Geometry Perspectivecited by 25
  27. 2020Neuron Merging: Compensating for Pruned Neuronscited by 24
  28. 2017Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networkscited by 21
  29. 2021Joint Matrix Decomposition for Deep Convolutional Neural Networks Compressioncited by 10
  30. 2019CUP: Cluster Pruning for Compressing Deep Neural Networkscited by 7
  31. 2016Dynamical Systems On Weighted Lattices: General Theorycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Sparsity is Combinatorial Depth: Quantifying MoE Expressivity via Tropical Geometrycited by 3
  2. 2026Geometric Capacity of Transformers: A Tropical Geometry Perspectivecited by 1
  3. 2026UltraLIF: Fully Differentiable Spiking Neural Networks via Ultradiscretization and Max-Plus Algebracited by 0