# Campfire: Compressible, Regularization-Free, Structured Sparse Training for Hardware Accelerators

Source: [Campfire: Compressible, Regularization-Free, Structured Sparse Training for Hardware Accelerators](<https://www.sota2.com/research/paper/68fa66e51e209131cea12ec8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:01:21.007Z

Authors: Noah Gamboa, Kais Kudrolli, Anand Dhoot, Ardavan Pedram

Published: 2020-01-09T23:15:43.000Z

## Abstract

This paper studies structured sparse training of CNNs with a gradual pruning technique that leads to fixed, sparse weight matrices after a set number of epochs. We simplify the structure of the enforced sparsity so that it reduces overhead caused by regularization. The proposed training methodology Campfire explores pruning at granularities within a convolutional kernel and filter.   We study various tradeoffs with respect to pruning duration, level of sparsity, and learning rate configuration. We show that our method creates a sparse version of ResNet-50 and ResNet-50 v1.5 on full ImageNet while remaining within a negligible \<1% margin of accuracy loss. To ensure that this type of sparse training does not harm the robustness of the network, we also demonstrate how the network behaves in the presence of adversarial attacks. Our results show that with 70% target sparsity, over 75% top-1 accuracy is achievable.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2001.03253>)

[PDF](<https://arxiv.org/pdf/2001.03253.pdf>)