arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.07501cs.LGcs.NAmath.NAstat.ML
收藏

在监督、无监督和强化学习中对时间序列预测施加约束

Enforcing constraints for time series prediction in supervised, unsupervised and reinforcement learning

Advanced Computing, Mathematics and Data Division, Pacific Northwest National Laboratory(太平洋西北国家实验室高级计算、数学与数据部门)

Panos Stinis

AI总结:

本文研究了如何在监督、无监督和强化学习中通过施加来自动态系统的约束来加速深度神经网络训练并提高其预测能力,主要贡献是提出了一种基于动作价值函数同伦的新型方法来稳定和加速强化学习训练。

摘要:

我们假设我们给定了一个来自动态系统的数据时间序列,我们的任务是学习动态系统的流映射。我们提出了关于如何施加来自动态系统的约束以加速深度神经网络训练并提高其预测能力的一系列结果。特别是,我们为监督、无监督和强化学习三种主要学习模式提供了在训练过程中施加约束的方法。一般来说,动态约束需要包括类似于模型降阶形式中的记忆项。这些记忆项起到恢复力的作用,纠正由学习的流映射在预测过程中犯的错误。对于监督学习,约束被添加到目标函数中。对于无监督学习,特别是生成对抗网络,约束是通过增强判别器的输入引入的。最后,对于强化学习,特别是actor-critic方法,约束被添加到奖励函数中。此外,对于强化学习情况,我们提出了一种基于动作价值函数同伦的新方法,以稳定和加速训练。我们使用洛伦兹系统数值结果来说明各种构造。

英文摘要:

We assume that we are given a time series of data from a dynamical system and our task is to learn the flow map of the dynamical system. We present a collection of results on how to enforce constraints coming from the dynamical system in order to accelerate the training of deep neural networks to represent the flow map of the system as well as increase their predictive ability. In particular, we provide ways to enforce constraints during training for all three major modes of learning, namely supervised, unsupervised and reinforcement learning. In general, the dynamic constraints need to include terms which are analogous to memory terms in model reduction formalisms. Such memory terms act as a restoring force which corrects the errors committed by the learned flow map during prediction. For supervised learning, the constraints are added to the objective function. For the case of unsupervised learning, in particular generative adversarial networks, the constraints are introduced by augmenting the input of the discriminator. Finally, for the case of reinforcement learning and in particular actor-critic methods, the constraints are added to the reward function. In addition, for the reinforcement learning case, we present a novel approach based on homotopy of the action-value function in order to stabilize and accelerate training. We use numerical results for the Lorenz system to illustrate the various constructions.

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。

↑