paper-with-me

Papers

Pruning Convolutional Filters via Reinforcement Learning with Entropy Minimization

2023-12-08 · Bogdan Musat, Razvan Andonie

Structural pruning has become an integral part of neural network optimization, used to achieve architectural configurations which can be deployed and run more efficiently on embedded devices. Previous results showed that pruning is possible with minimum performance loss by utilizing a reinforcement learning agent which makes decisions about the sparsity level of each neural layer by maximizing as a reward the accuracy of the network. We introduce a novel information-theoretic reward function which minimizes the spatial entropy of convolutional activations. This minimization ultimately acts as a proxy for maintaining accuracy, although these two criteria are not related in any way. Our method shows that there is another possibility to preserve accuracy without the need to directly optimize it in the agent's reward function. In our experiments, we were able to reduce the total number of FLOPS of multiple popular neural network architectures by 5-10x, incurring minimal or no performance drop and being on par with the solution found by maximizing the accuracy.

📄 PDF Abstract BibTeX arXiv:2312.04918

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Accelerating Convolutional Neural Network Pruning via Spatial Aura Entropy

2023-12-08 · Bogdan Musat, Razvan Andonie

In recent years, pruning has emerged as a popular technique to reduce the computational complexity and memory footprint of Convolutional Neural Network (CNN) models. Mutual Information (MI) has been widely used as a crit…

Computational EfficiencyNetwork Pruning

RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Acceleration

2024-11-10 · Boyao Wang, Volodymyr Kindratenko

Convolutional Neural Networks (CNNs) have demonstrated exceptional performance in recent years. Compressing these models not only reduces storage requirements, making deployment to edge devices feasible, but also acceler…

Rethinking the Pruning Criteria for Convolutional Neural Network

2021-01-01 · NeurIPS 2021 12 · Zhongzhan Huang, Xinjiang Wang, Ping Luo

Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), and various pruning criteria have been proposed to remove the redundant filters of CNNs. From our comprehensive experiments, we…

LEAN: graph-based pruning for convolutional neural networks by extracting longest chains

2021-09-29 · Richard Arnoud Schoonhoven, Allard Hendriksen, Daniel Pelt, Joost Batenburg

Neural network pruning techniques can substantially reduce the computational cost of applying convolutional neural networks (CNNs). Common pruning methods determine which convolutional filters to remove by ranking the fi…

Network Pruning

Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning

2020-04-24 · Zhongzhan Huang, Wenqi Shao, Xinjiang Wang, Liang Lin 외

Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), where various pruning criteria have been proposed to remove the redundant filters. From our comprehensive experiments, we found…