paper-with-me

홈 › Papers

Comparing Rewinding and Fine-tuning in Neural Network Pruning

2020-03-05 · ICLR 2020 1 · Alex Renda, Jonathan Frankle, Michael Carbin

Many neural network pruning algorithms proceed in three steps: train the network to completion, remove unwanted structure to compress the network, and retrain the remaining structure to recover lost accuracy. The standard retraining technique, fine-tuning, trains the unpruned weights from their final trained values using a small fixed learning rate. In this paper, we compare fine-tuning to alternative retraining techniques. Weight rewinding (as proposed by Frankle et al., (2019)), rewinds unpruned weights to their values from earlier in training and retrains them from there using the original training schedule. Learning rate rewinding (which we propose) trains the unpruned weights from their final values using the same learning rate schedule as weight rewinding. Both rewinding techniques outperform fine-tuning, forming the basis of a network-agnostic pruning algorithm that matches the accuracy and compression ratios of several more network-specific state-of-the-art techniques.

📄 PDF Abstract BibTeX arXiv:2003.02389

Code (2)

lottery-ticket/rewinding-iclr20-public 공식 구현 tf
gahaalt/reproducing-comparing-rewinding-and-finetuning tf

Tasks

Network Pruning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Reproducibility Study: Comparing Rewinding and Fine-tuning in Neural Network Pruning

2021-09-20 · Szymon Mikler

Scope of reproducibility: We are reproducing Comparing Rewinding and Fine-tuning in Neural Networks from arXiv:2003.02389. In this work the authors compare three different approaches to retraining neural networks after p…

Network Pruning

Network Pruning That Matters: A Case Study on Retraining Variants

2021-05-07 · ICLR 2021 1 · Duong H. Le, Binh-Son Hua

Network pruning is an effective method to reduce the computational expense of over-parameterized neural networks for deployment on low-resource systems. Recent state-of-the-art techniques for retraining pruned networks s…

Network PruningSentence

ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networks

2025-05-12 · Wenhao Hu, Paul Henderson, José Cano

Pruning is a widely used method for compressing Deep Neural Networks (DNNs), where less relevant parameters are removed from a DNN model to reduce its size. However, removing parameters reduces model accuracy, so pruning…

Cascade Weight Shedding in Deep Neural Networks: Benefits and Pitfalls for Network Pruning

2021-03-19 · Kambiz Azarian, Fatih Porikli

We report, for the first time, on the cascade weight shedding phenomenon in deep neural networks where in response to pruning a small percentage of a network's weights, a large percentage of the remaining is shed over a …

Network Pruning

Layer-adaptive sparsity for the Magnitude-based Pruning

2020-10-15 · ICLR 2021 1 · Jaeho Lee, Sejun Park, Sangwoo Mo, Sungsoo Ahn 외

Recent discoveries on neural network pruning reveal that, with a carefully chosen layerwise sparsity, a simple magnitude-based pruning achieves state-of-the-art tradeoff between sparsity and performance. However, without…

image-classificationImage ClassificationNetwork Pruning