mlsanityData to 14 Oct 2026

Compression Aware Certified Training

arXiv 2506.11992 ↗First posted 13 Jun 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep neural networks deployed in safety-critical, resource-constrained environments must balance efficiency and robustness. Existing methods treat compression and certified robustness as separate goals, compromising either efficiency or safety. We propose CACTUS (Compression Aware Certified Training Using network Sets), a general framework for unifying these objectives during training. CACTUS models maintain high certified accuracy even when compressed. We apply CACTUS for both pruning and quantization and show that it effectively trains models which can be efficiently compressed while maintaining high accuracy and certifiable robustness. CACTUS achieves state-of-the-art accuracy and certified performance for both pruning and quantization on a variety of datasets and input specifications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 52 references that are in the map. First posted on arXiv 13 Jun 2025.

Builds on

31 of 52 references.

References · 31

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  5. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  6. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  7. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  8. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  9. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,121
  10. 2016End to End Learning for Self-Driving Carscited by 1,009
  11. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 906
  12. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
19 more
  1. 2019Learned Step Size Quantizationcited by 628
  2. 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
  3. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
  4. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 443
  5. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 205
  6. 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 202
  7. 2020Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluationcited by 188
  8. 2020Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifierscited by 187
  9. 2018Training for Faster Adversarial Robustness Verification via Inducing ReLU Stabilitycited by 67
  10. 2022Certified Training: Small Boxes are All You Needcited by 52
  11. 2021Fast Certified Robust Training with Short Warmupcited by 46
  12. 2023Expressive Losses for Verified Robustness via Convex Combinationscited by 23
  13. 2022Compression-aware Training of Neural Networks using Frank-Wolfecited by 16
  14. 2022Can pruning improve certified robustness of neural networks?cited by 14
  15. 2020Adversarial Training and Provable Robustness: A Tale of Two Objectivescited by 12
  16. 2023TAPS: Connecting Certified and Adversarial Trainingcited by 11
  17. 2024Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustnesscited by 10
  18. 2022Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networkscited by 3
  19. 2023Exploring the Performance of Pruning Methods in Neural Networks: An Empirical Study of the Lottery Ticket Hypothesiscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions
  2. 2026Few Bits, One Law: Toward W2A4KV2
  3. 2022CrAM: A Compression-Aware Minimizer
  4. 2021LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time
  5. 2022Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning
  6. 2025Optimizing Deep Neural Networks using Safety-Guided Self Compression
  7. 2024"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach
  8. 2023Towards Optimal Compression: Joint Pruning and Quantization