用参数延续法优化神经网络，提升训练效果
Principled Curriculum Learning using Parameter Continuation Methods
- 通过参数延续方法实现渐进式训练
- 在监督与无监督任务中优于ADAM等先进优化器
- 理论扎实且适用于多种深度学习场景
本文提出一种用于神经网络优化的参数延续方法。参数延续、同伦方法与课程学习之间存在紧密联系。所提方法在理论上具有依据，在多个深度神经网络问题上表现出实际有效性。特别地，我们在监督与无监督学习任务中展示了优于当前最优优化技术（如ADAM）的泛化性能。
原文摘要 · Abstract (English)
In this work, we propose a parameter continuation method for the optimization of neural networks. There is a close connection between parameter continuation, homotopies, and curriculum learning. The methods we propose here are theoretically justified and practically effective for several problems in deep neural networks. In particular, we demonstrate better generalization performance than state-of-the-art optimization techniques such as ADAM for supervised and unsupervised learning tasks.
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。