paper-with-me

홈 › Papers

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

2025-07-20 · Ganesh Sundaram, Jonas Ulmen, Amjad Haider, Daniel Görges 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.

📄 PDF Abstract BibTeX arXiv:2507.14882

Code (0)

등록된 구현이 없습니다.

Tasks

Model Compression

Similar Papers 제목 키워드 기반

Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis

2025-04-17 · Ganesh Sundaram, Jonas Ulmen, Daniel Görges

Deep neural networks (DNNs) deliver outstanding performance, but their complexity often prohibits deployment in resource-constrained settings. Comprehensive structured pruning frameworks based on parameter dependency ana…

Hessian-Aware Pruning and Optimal Neural Implant

2021-01-22 · Shixing Yu, Zhewei Yao, Amir Gholami, Zhen Dong 외

Pruning is an effective method to reduce the memory footprint and FLOPs associated with neural network models. However, existing structured-pruning methods often result in significant accuracy degradation for moderate pr…

Sensitivity

Transfer Learning for Structured Pruning under Limited Task Data

2023-11-10 · Lucio Dery, David Grangier, Awni Hannun

Large, pre-trained models are problematic to use in resource constrained applications. Fortunately, task-aware structured pruning methods offer a solution. These approaches reduce model size by dropping structural units …

Transfer Learning

DarwinLM: Evolutionary Structured Pruning of Large Language Models

2025-02-11 · Shengkun Tang, Oliver Sieberling, Eldar Kurtic, Zhiqiang Shen 외

Large Language Models (LLMs) have achieved significant success across various NLP tasks. However, their massive computational costs limit their widespread use, particularly in real-time applications. Structured pruning o…

Model Compression

Sample-aware Adaptive Structured Pruning for Large Language Models

2025-03-08 · Jun Kong, Xinge Ma, Jin Wang, Xuejie Zhang

Large language models (LLMs) have achieved outstanding performance in natural language processing, but enormous model sizes and high computational costs limit their practical deployment. Structured pruning can effectivel…

Bayesian Optimization