arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.05151cs.LGcs.AI
收藏

有效神经网络训练的可证数据子集选择

Provable Data Subset Selection For Efficient Neural Network Training

DataHeroes(DataHeroes公司);Rice University(莱斯大学);University of Haifa(海法大学)

Murad Tukan, Samson Zhou, Alaa Maalouf, Daniela Rus, Vladimir Braverman, Dan Feldman

摘要:

径向基函数神经网络(\emph{RBFNN})是众所周知的,因为它们能够在给定足够的隐藏神经元的情况下以任意精度逼近封闭有界集上的任何连续函数。在本文中,我们介绍了构造\emph{RBFNNs}核心集的第一个算法,即,小的加权子集,其近似任何径向基函数网络上的输入数据的损失,并且因此近似由较大输入数据上的\emph{RBFNN}定义的任何函数。特别地,我们构造了径向基和拉普拉斯损失函数的核心集。然后,我们使用我们的核心集来获得用于训练深度神经网络的可证明数据子集选择算法。由于我们的核心集近似于每个函数,它们也近似于神经网络中每个权重的梯度,这是输入上的一个特定函数。然后,我们在流行的网络架构和数据集上对函数逼近和数据集子集选择进行了实证评估,证明了我们的核心集构造的有效性和准确性。

英文摘要:

Radial basis function neural networks (\emph{RBFNN}) are {well-known} for their capability to approximate any continuous function on a closed bounded set with arbitrary precision given enough hidden neurons. In this paper, we introduce the first algorithm to construct coresets for \emph{RBFNNs}, i.e., small weighted subsets that approximate the loss of the input data on any radial basis function network and thus approximate any function defined by an \emph{RBFNN} on the larger input data. In particular, we construct coresets for radial basis and Laplacian loss functions. We then use our coresets to obtain a provable data subset selection algorithm for training deep neural networks. Since our coresets approximate every function, they also approximate the gradient of each weight in a neural network, which is a particular function on the input. We then perform empirical evaluations on function approximation and dataset subset selection on popular network architectures and data sets, demonstrating the efficacy and accuracy of our coreset construction.

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。

↑