用贝叶斯优化自动调参，让神经网络更快更准地训练。
Bayesian Optimization for Hyperparameters Tuning in Neural Networks
- 基于高斯过程和置信上界，智能搜索最优超参数。
- 实验表明只需少量尝试就达到媲美人工调参的性能。
- 适合希望省时省力提升模型效果的研究者使用。
本研究探讨了贝叶斯优化（BO）在神经网络超参数调优中的应用，重点提升卷积神经网络（CNN）在图像分类任务中的表现。贝叶斯优化是一种适用于昂贵黑箱函数、连续输入且评估预算有限的无导数全局优化方法。该算法利用高斯过程回归与上置信界（UCB）和期望改进（EI）等采集函数，高效识别最优配置。通过Ax和BOTorch框架实现，实验表明BO能显著减少调参尝试次数，同时获得具有竞争力的模型性能。结果验证了其在探索与利用间良好平衡，快速收敛至最优CNN结构设置。该方法凸显了自动化神经网络调优的潜力，有助于提升机器学习流程中的准确率与计算效率。
原文摘要 · Abstract (English)
This study investigates the application of Bayesian Optimization (BO) for the hyperparameter tuning of neural networks, specifically targeting the enhancement of Convolutional Neural Networks (CNN) for image classification tasks. Bayesian Optimization is a derivative-free global optimization method suitable for expensive black-box functions with continuous inputs and limited evaluation budgets. The BO algorithm leverages Gaussian Process regression and acquisition functions like Upper Confidence Bound (UCB) and Expected Improvement (EI) to identify optimal configurations effectively. Using the Ax and BOTorch frameworks, this work demonstrates the efficiency of BO in reducing the number of hyperparameter tuning trials while achieving competitive model performance. Experimental outcomes reveal that BO effectively balances exploration and exploitation, converging rapidly towards optimal settings for CNN architectures. This approach underlines the potential of BO in automating neural network tuning, contributing to improved accuracy and computational efficiency in machine learning pipelines.
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。