mlsanityData to 14 Oct 2026

Channel Pruning In Quantization-aware Training: An Adaptive Projection-gradient Descent-shrinkage-splitting Method

arXiv 2204.04375 ↗First posted 9 Apr 2022cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose an adaptive projection-gradient descent-shrinkage-splitting method (APGDSSM) to integrate penalty based channel pruning into quantization-aware training (QAT). APGDSSM concurrently searches weights in both the quantized subspace and the sparse subspace. APGDSSM uses shrinkage operator and a splitting technique to create sparse weights, as well as the Group Lasso penalty to push the weight sparsity into channel sparsity. In addition, we propose a novel complementary transformed l1 penalty to stabilize the training for extreme compression.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 17 references that are in the map. First posted on arXiv 9 Apr 2022.

Builds on

12 of 17 references.

References · 12

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018Rethinking the Value of Network Pruningcited by 599
  3. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  4. 2016Learning Structured Sparsity in Deep Neural Networkscited by 541
  5. 2019Adversarial Robustness vs Model Compression, or Both?cited by 98
  6. 2016Training Neural Networks Without Gradients: A Scalable ADMM Approachcited by 61
  7. 2018BinaryRelax: A Relaxation Approach For Training Deep Neural Networks With Quantized Weightscited by 24
  8. 2021Demystifying and Generalizing BinaryConnectcited by 11
  9. 2020Sparsity Meets Robustness: Channel Pruning for the Feynman-Kac Formalism Principled Robust Deep Neural Netscited by 8
  10. 2020An Integrated Approach to Produce Robust Models with High Efficiencycited by 2
  11. 2018Convergence of a Relaxed Variable Splitting Method for Learning Sparse Neural Networks via ℓ1, ℓ0, and transformed-ℓ1 Penaltiescited by 1
  12. 2019A Channel-Pruned and Weight-Binarized Convolutional Neural Network for Keyword Spottingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025CoDeQ: End-to-End Joint Model Compression with Dead-Zone Quantizer for High-Sparsity and Low-Precision Networks
  2. 2025AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent
  3. 2026Q-MINO: A Minimal-Norm Method for Quantization-Aware Training
  4. 2026Low-Dimensional High-Leverage Subspace Optimization: Beyond Full-Parameter Coupled Training for Neural Network Quantization
  5. 2025SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions
  6. 2021Quantized Proximal Averaging Network for Analysis Sparse Coding
  7. 2023On Uniform Scalar Quantization for Learned Image Compression
  8. 2022QFT: Post-training quantization via fast joint finetuning of all degrees of freedom