对比多种优化器在股市预测中的表现，提出新优化器提升训练速度与稳定性。
From Rattle to Roar: Optimizer Showdown for MambaStock on S&P 500
- 融合Lion的快速训练与梯度平滑优势，设计新型优化器Roaree
- Adam/RMSProp在测试误差上最优，Lion训练速度最快
- 适合追求高效训练的金融时序建模研究者
我们评估了多种优化器在使用MambaStock模型预测标普500指数收益任务中的表现。在常用算法中，梯度平滑与自适应率优化器（如Adam和RMSProp）取得最低测试误差；相比之下，Lion优化器展现出显著更快的训练速度。为结合两者优势，我们提出一类新型优化器Roaree，能抑制Lion常有的振荡损失行为，同时保持其训练速度。
原文摘要 · Abstract (English)
We evaluate the performance of several optimizers on the task of forecasting S&P 500 Index returns with the MambaStock model. Among the most widely used algorithms, gradient-smoothing and adaptive-rate optimizers (for example, Adam and RMSProp) yield the lowest test errors. In contrast, the Lion optimizer offers notably faster training. To combine these advantages, we introduce a novel family of optimizers, Roaree, that dampens the oscillatory loss behavior often seen with Lion while preserving its training speed.
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。