用进化算法自动优化模型，让神经网络更小更快更省资源。
Automated Evolutionary Optimization for Resource-Efficient Neural Network Training
- 通过进化算法自动搜索压缩与训练策略组合
- 模型大小减75%，延迟降33%，吞吐量升13%
- 适合追求高效部署的工业级模型开发者
神经网络优化面临分布式计算、压缩技术和高效训练等多重挑战，而对可扩展、资源高效的模型需求日益增长。为此，我们提出新型自动化机器学习框架PETRA，采用进化优化方法联合优化模型架构与训练策略，集成剪枝、量化和损失正则化。在金融事件序列、图像和时间序列等真实数据集上的实验表明，PETRA显著提升模型性能与可扩展性：模型规模最大减少75%，延迟降低33%，吞吐量提高13%，且目标指标无明显下降。
原文摘要 · Abstract (English)
There are many critical challenges in optimizing neural network models, including distributed computing, compression techniques, and efficient training, regardless of their application to specific tasks. Solving such problems is crucial because the need for scalable and resource-efficient models is increasing. To address these challenges, we have developed a new automated machine learning (AutoML) framework, Parameter Efficient Training with Robust Automation (PETRA). It applies evolutionary optimization to model architecture and training strategy. PETRA includes pruning, quantization, and loss regularization. Experimental studies on real-world data with financial event sequences, as well as image and time-series -- benchmarks, demonstrate PETRA's ability to improve neural model performance and scalability -- namely, a significant decrease in model size (up to 75%) and latency (up to 33%), and an increase in throughput (by 13%) without noticeable degradation in the target metric.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。