# Sparsity Meets Robustness: Channel Pruning for the Feynman-Kac Formalism Principled Robust Deep Neural Nets

arXiv: https://arxiv.org/abs/2003.00631 · HTML: https://mlsanity.com/paper/2003.00631/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2020.

## Built on by (most cited first, 8 of 8)

- [0/1 Deep Neural Networks via Block Coordinate Descent](https://mlsanity.com/paper/2206.09379/) (2022)
- [Proximal Implicit ODE Solvers for Accelerating Learning Neural ODEs](https://mlsanity.com/paper/2204.08621/) (2022)
- [A Convex-optimization-based Layer-wise Post-training Pruner for Large Language Models](https://mlsanity.com/paper/2408.03728/) (2024)
- [Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility](https://mlsanity.com/paper/2507.17748/) (2025)
- [glassoformer: a query-sparse transformer for post-fault power grid voltage prediction](https://mlsanity.com/paper/2201.09145/) (2022)
- [Enhancing Zero-Shot Many to Many Voice Conversion with Self-Attention VAE](https://mlsanity.com/paper/2203.16037/) (2022)
- [Supervised Robustness-preserving Data-free Neural Network Pruning](https://mlsanity.com/paper/2204.00783/) (2022)
- [Channel Pruning In Quantization-aware Training: An Adaptive Projection-gradient Descent-shrinkage-splitting Method](https://mlsanity.com/paper/2204.04375/) (2022)

## Abstract (arXiv)

Deep neural nets (DNNs) compression is crucial for adaptation to mobile devices. Though many successful algorithms exist to compress naturally trained DNNs, developing efficient and stable compression algorithms for robustly trained DNNs remains widely open. In this paper, we focus on a co-design of efficient DNN compression algorithms and sparse neural architectures for robust and accurate deep learning. Such a co-design enables us to advance the goal of accommodating both sparsity and robustness. With this objective in mind, we leverage the relaxed augmented Lagrangian based algorithms to prune the weights of adversarially trained DNNs, at both structured and unstructured levels. Using a Feynman-Kac formalism principled robust and sparse DNNs, we can at least double the channel sparsity of the adversarially trained ResNet20 for CIFAR10 classification, meanwhile, improve the natural accuracy by 8.69% and the robust accuracy under the benchmark 20 iterations of IFGSM attack by 5.42%. The code is available at urlhttps://github.com/BaoWangMath/rvsm-rgsm-admm.