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 1803.09522cs.LGstat.ML
收藏

一个可证明正确的深度学习算法,实际上是有效的

A Provably Correct Algorithm for Deep Learning that Actually Works

The Hebrew University(希伯来大学)

Eran Malach, Shai Shalev-Shwartz

摘要:

我们描述了一种用于训练深度卷积网络的逐层算法,其中每一步都涉及两层网络的梯度更新,然后是一个简单的聚类算法。我们的算法源于一个深层生成模型,该模型逐层生成图像,其中较低分辨率的图像对应于潜在语义类。我们分析算法的收敛速度,假设数据确实是根据这个模型生成的(以及其他假设)。虽然我们并不假装声称这些假设对于自然图像是现实的,但我们确实相信它们捕捉到了真实数据的一些真实属性。此外,我们证明了我们的算法实际上在实践中(在CIFAR数据集上)有效,与通过随机梯度下降训练的香草卷积神经网络的结果相同。最后,我们的证明技术可能是独立的利益。

英文摘要:

We describe a layer-by-layer algorithm for training deep convolutional networks, where each step involves gradient updates for a two layer network followed by a simple clustering algorithm. Our algorithm stems from a deep generative model that generates mages level by level, where lower resolution images correspond to latent semantic classes. We analyze the convergence rate of our algorithm assuming that the data is indeed generated according to this model (as well as additional assumptions). While we do not pretend to claim that the assumptions are realistic for natural images, we do believe that they capture some true properties of real data. Furthermore, we show that our algorithm actually works in practice (on the CIFAR dataset), achieving results in the same ballpark as that of vanilla convolutional neural networks that are being trained by stochastic gradient descent. Finally, our proof techniques may be of independent interest.

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。

↑