arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.13420cs.LGstat.ML
收藏

时间序列回归和连续规范化流的离散化优化与优化离散化

Discretize-Optimize vs. Optimize-Discretize for Time-Series Regression and Continuous Normalizing Flows

Emory University(埃默里大学)

Derek Onken, Lars Ruthotto

摘要:

我们比较了离散优化(Disc-Opt)和优化离散(Opt-Disc)方法,用于使用神经ODE的时间序列回归和连续归一化流(CNFs)。神经常微分方程是含有神经网络成分的常微分方程。训练神经常微分方程是一个最优控制问题,其中权值是控制,隐藏特征是状态。每次训练迭代都涉及向前求解一个ODE和向后求解另一个ODE,这可能需要大量的计算、时间和内存。在图像分类任务中比较Opt-Disc和Disc-Opt方法,Gholami等人(2019)认为,由于保证了梯度的准确性,Disc-Opt更可取。在本文中,我们将比较扩展到时间序列回归和CNFs的神经ODE。与分类不同,这些任务中有意义的模型还必须满足精确的最终时间输出之外的其他要求,例如,CNF的可逆性。通过我们的数值实验,我们证明了通过仔细的数值处理,Disc-Opt方法可以在大幅降低训练成本的情况下实现与Opt-Disc相似的推理性能。Disc-Opt在七个独立问题中的六个中降低了成本,培训时间减少了39%到97%,在一个案例中,Disc-Opt将培训从9天减少到不到1天。

英文摘要:

We compare the discretize-optimize (Disc-Opt) and optimize-discretize (Opt-Disc) approaches for time-series regression and continuous normalizing flows (CNFs) using neural ODEs. Neural ODEs are ordinary differential equations (ODEs) with neural network components. Training a neural ODE is an optimal control problem where the weights are the controls and the hidden features are the states. Every training iteration involves solving an ODE forward and another backward in time, which can require large amounts of computation, time, and memory. Comparing the Opt-Disc and Disc-Opt approaches in image classification tasks, Gholami et al. (2019) suggest that Disc-Opt is preferable due to the guaranteed accuracy of gradients. In this paper, we extend the comparison to neural ODEs for time-series regression and CNFs. Unlike in classification, meaningful models in these tasks must also satisfy additional requirements beyond accurate final-time output, e.g., the invertibility of the CNF. Through our numerical experiments, we demonstrate that with careful numerical treatment, Disc-Opt methods can achieve similar performance as Opt-Disc at inference with drastically reduced training costs. Disc-Opt reduced costs in six out of seven separate problems with training time reduction ranging from 39% to 97%, and in one case, Disc-Opt reduced training from nine days to less than one day.

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。

↑