paper-with-me

홈 › Papers

Pruning Early Exit Networks

2022-07-08 · Alperen Görmez, Erdem Koyuncu

Deep learning models that perform well often have high computational costs. In this paper, we combine two approaches that try to reduce the computational cost while keeping the model performance high: pruning and early exit networks. We evaluate two approaches of pruning early exit networks: (1) pruning the entire network at once, (2) pruning the base network and additional linear classifiers in an ordered fashion. Experimental results show that pruning the entire network at once is a better strategy in general. However, at high accuracy rates, the two approaches have a similar performance, which implies that the processes of pruning and early exit can be separated without loss of optimality.

📄 PDF Abstract BibTeX arXiv:2207.03644

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
BASE 설명 없음

Similar Papers 제목 키워드 기반

Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning

2021-10-30 · Xuanli He, Iman Keivanloo, Yi Xu, Xiang He 외

Pre-training and then fine-tuning large language models is commonly used to achieve state-of-the-art performance in natural language processing (NLP) tasks. However, most pre-trained models suffer from low inference spee…

text-classificationText Classification

Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Pre-training and then fine-tuning large language models is commonly used to achieve state-of-the-art performance in natural language processing (NLP) tasks. However, most pre-trained models suffer from low inference spe…

text-classificationText Classification

Dynamic Vocabulary Pruning in Early-Exit LLMs

2024-10-24 · Jort Vincenti, Karim Abdel Sadek, Joan Velja, Matteo Nulli 외

Increasing the size of large language models (LLMs) has been shown to lead to better performance. However, this comes at the cost of slower and more expensive inference. Early-exiting is a promising approach for improvin…

When to Prune? A Policy towards Early Structural Pruning

2021-10-22 · CVPR 2022 1 · Maying Shen, Pavlo Molchanov, Hongxu Yin, Jose M. Alvarez

Pruning enables appealing reductions in network memory footprint and time complexity. Conventional post-training pruning techniques lean towards efficient inference while overlooking the heavy computation for training. R…

GPUNetwork Pruning

DRIVE: Dual Gradient-Based Rapid Iterative Pruning

2024-04-01 · Dhananjay Saikumar, Blesson Varghese

Modern deep neural networks (DNNs) consist of millions of parameters, necessitating high-performance computing during training and inference. Pruning is one solution that significantly reduces the space and time complexi…