arXiv:2412.06686cs.LGphysics.comp-ph2024-12被引 1
针对算子学习，总结了高效训练的超参与方法选择。
Some Best Practices in Operator Learning
- 系统测试激活函数、丢弃率和随机权重平均等配置
- 发现特定组合在多类微分方程上表现更稳定
- 适合从事算子学习研究或模型调优的开发者
超参数搜索计算成本高昂。本文针对算子学习任务，研究了几种通用的超参数设置与训练方法。以DeepONets、傅里叶神经算子和Koopman自编码器为例，在多个微分方程问题上考察了激活函数、丢弃率及随机权重平均等选项，旨在发现具有鲁棒性的训练趋势。结果表明，某些配置组合在不同模型与方程间表现出更一致的性能，有助于提升训练效率与泛化能力。
原文摘要 · Abstract (English)
Hyperparameters searches are computationally expensive. This paper studies some general choices of hyperparameters and training methods specifically for operator learning. It considers the architectures DeepONets, Fourier neural operators and Koopman autoencoders for several differential equations to find robust trends. Some options considered are activation functions, dropout and stochastic weight averaging.
算子学习超参优化深度学习
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。