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.

翻译：优化神经网络模型存在诸多关键挑战，包括分布式计算、压缩技术和高效训练，无论其应用于何种具体任务。解决此类问题至关重要，因为对可扩展且资源高效模型的需求日益增长。为应对这些挑战，我们开发了一种新的自动化机器学习（AutoML）框架——参数高效训练与鲁棒自动化（PETRA）。该框架将进化优化应用于模型架构和训练策略。PETRA包含剪枝、量化和损失正则化技术。在真实世界金融事件序列数据以及图像和时间序列基准测试上的实验研究表明，PETRA能够提升神经模型的性能和可扩展性——具体表现为模型尺寸显著减小（最高达75%）、延迟降低（最高达33%）、吞吐量提升（13%），且目标指标未出现明显下降。