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 1807.07540stat.MLcs.LG
收藏

贝叶斯滤波统一了自适应和非自适应神经网络优化方法

Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods

University of Bristol(布里斯托大学)

Laurence Aitchison

摘要:

我们将神经网络优化问题表述为贝叶斯滤波,其中观测值是反向传播的梯度。虽然神经网络优化之前已经使用与贝叶斯推断密切相关的自然梯度方法进行了研究,但他们无法使用均方根梯度归一化器恢复标准优化器,如Adam和RMSprop,而是得到均方归一化器。为了恢复均方根归一化,我们发现有必要考虑所有其他参数的时间动态,因为它们正在优化。由此产生的优化器AdaBayes自适应地在类SGD和类Adam行为之间转换,自动恢复AdamW,这是Adam的最新变体,具有解耦的权重衰减,并且具有与SGD竞争的泛化性能。

英文摘要:

We formulate the problem of neural network optimization as Bayesian filtering, where the observations are the backpropagated gradients. While neural network optimization has previously been studied using natural gradient methods which are closely related to Bayesian inference, they were unable to recover standard optimizers such as Adam and RMSprop with a root-mean-square gradient normalizer, instead getting a mean-square normalizer. To recover the root-mean-square normalizer, we find it necessary to account for the temporal dynamics of all the other parameters as they are geing optimized. The resulting optimizer, AdaBayes, adaptively transitions between SGD-like and Adam-like behaviour, automatically recovers AdamW, a state of the art variant of Adam with decoupled weight decay, and has generalisation performance competitive with SGD.

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。

↑