# Application-Specific Component-Aware Structured Pruning of Deep Neural Networks in Control via Soft Coefficient Optimization

arXiv: https://arxiv.org/abs/2507.14882 · HTML: https://mlsanity.com/paper/2507.14882/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 20 Jul 2025.

## Builds on (most cited first, 13 of 13)

- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations](https://mlsanity.com/paper/2308.06767/) (2023)
- [LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights](https://mlsanity.com/paper/2404.11936/) (2024)
- [How to Train Your Neural Control Barrier Function: Learning Safety Filters for Complex Input-Constrained Systems](https://mlsanity.com/paper/2310.15478/) (2023)
- [Neural Lyapunov Control of Unknown Nonlinear Systems with Stability Guarantees](https://mlsanity.com/paper/2206.01913/) (2022)
- [Fast as CHITA: Neural Network Pruning with Combinatorial Optimization](https://mlsanity.com/paper/2302.14623/) (2023)
- [Data-Efficient Structured Pruning via Submodular Optimization](https://mlsanity.com/paper/2203.04940/) (2022)
- [Structurally Prune Anything: Any Architecture, Any Framework, Any Time](https://mlsanity.com/paper/2403.18955/) (2024)
- [Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis](https://mlsanity.com/paper/2504.13296/) (2025)
- [Small Contributions, Small Networks: Efficient Neural Network Pruning Based on Relative Importance](https://mlsanity.com/paper/2410.16151/) (2024)

## Abstract (arXiv)

Deep neural networks (DNNs) offer significant flexibility and robust performance. This makes them ideal for building not only system models but also advanced neural network controllers (NNCs). However, their high complexity and computational needs often limit their use. Various model compression strategies have been developed over the past few decades to address these issues. These strategies are effective for general DNNs but do not directly apply to NNCs. NNCs need both size reduction and the retention of key application-specific performance features. In structured pruning, which removes groups of related elements, standard importance metrics often fail to protect these critical characteristics. In this paper, we introduce a novel framework for calculating importance metrics in pruning groups. This framework not only shrinks the model size but also considers various application-specific constraints. To find the best pruning coefficient for each group, we evaluate two approaches. The first approach involves simple exploration through grid search. The second utilizes gradient descent optimization, aiming to balance compression and task performance. We test our method in two use cases: one on an MNIST autoencoder and the other on a Temporal Difference Model Predictive Control (TDMPC) agent. Results show that the method effectively maintains application-relevant performance while achieving a significant reduction in model size.