arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.12263cs.LGcs.NEeess.SP
收藏

面向门控循环单元的基于遗传算法的定制化混合精度亚8比特量化方案

Towards a tailored mixed-precision sub-8-bit quantization scheme for Gated Recurrent Units using Genetic Algorithms

Technical University of Denmark(丹麦技术大学);GN Audio(GN音频公司)

Riccardo Miccini, Alessandro Cerioli, Clément Laroche, Tobias Piechowiak, Jens Sparsø, Luca Pezzarossa

AI总结:

针对GRU亚8比特量化难调优的问题,提出算子比特宽独立可选的模块化整数量化方案,用遗传算法搜索最优比特宽组合,在四个序列任务上实现25%-55%模型压缩且精度媲美8比特均匀量化。

摘要:

尽管深度神经网络的模型压缩技术近年来取得了进展,但将此类模型部署在超低功耗嵌入式设备上仍具挑战。尤其是门控循环单元(Gated Recurrent Units, GRU)的量化方案因依赖内部状态而难以调优,使其无法充分受益于亚8比特量化。本文提出了一种GRU的模块化整数量化方案,每个算子的比特宽度可独立选择。随后我们采用遗传算法(Genetic Algorithms, GA)探索庞大的候选比特宽度搜索空间,同时优化模型大小与准确率。我们在四个不同的序列任务上评估了所提方法,证明混合精度方案在帕累托效率方面优于均匀精度方案。实验结果显示,我们实现了25%至55%的模型大小缩减,同时保持了与8比特均匀精度相当的准确率。

英文摘要:

Despite the recent advances in model compression techniques for deep neural networks, deploying such models on ultra-low-power embedded devices still proves challenging. In particular, quantization schemes for Gated Recurrent Units (GRU) are difficult to tune due to their dependence on an internal state, preventing them from fully benefiting from sub-8bit quantization. In this work, we propose a modular integer quantization scheme for GRUs where the bit width of each operator can be selected independently. We then employ Genetic Algorithms (GA) to explore the vast search space of possible bit widths, simultaneously optimising for model size and accuracy. We evaluate our methods on four different sequential tasks and demonstrate that mixed-precision solutions exceed homogeneous-precision ones in terms of Pareto efficiency. In our results, we achieve a model size reduction between 25% and 55% while maintaining an accuracy comparable with the 8-bit homogeneous equivalent.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑