arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1905.09691stat.MLcs.LG
收藏

基于种群的RNN长期学习全局优化方法

Population-based Global Optimisation Methods for Learning Long-term Dependencies with RNNs

University of Oxford(牛津大学);Oxford-Man Institute of Quantitative Finance(牛津-曼量化金融研究所)

Bryan Lim, Stefan Zohren, Stephen Roberts

摘要:

尽管最近在网络架构和损失函数方面进行了创新,但由于基于梯度的优化方法的挑战,训练RNN学习长期依赖关系仍然很困难。受Deep Neuroevolution在强化学习中的成功启发(Such et al. 2017),我们探索了基于无梯度群体的全局优化(PBO)技术的使用-训练RNN以捕获时间序列数据中的长期依赖关系。测试进化策略(ES)和粒子群优化(PSO)在波动率预测的应用程序,我们表明,PBO方法导致的性能改善一般,ES表现出最一致的结果在各种架构。

英文摘要:

Despite recent innovations in network architectures and loss functions, training RNNs to learn long-term dependencies remains difficult due to challenges with gradient-based optimisation methods. Inspired by the success of Deep Neuroevolution in reinforcement learning (Such et al. 2017), we explore the use of gradient-free population-based global optimisation (PBO) techniques -- training RNNs to capture long-term dependencies in time-series data. Testing evolution strategies (ES) and particle swarm optimisation (PSO) on an application in volatility forecasting, we demonstrate that PBO methods lead to performance improvements in general, with ES exhibiting the most consistent results across a variety of architectures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑