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 2007.00884cs.LGstat.ML
收藏

基于神经切线核的神经网络算法的改进

A Revision of Neural Tangent Kernel-based Approaches for Neural Networks

Kyung-Su Kim, Aurélie C. Lozano, Eunho Yang

摘要:

最近基于神经切线核(NTK)的理论工作揭示了过参数化网络的优化和推广,并部分弥合了其实际成功与经典学习理论之间的差距。(1)推导出了训练误差界,表明网络能够很好地拟合任何有限的训练样本,反映了训练速度依赖于数据复杂度的更严格特征。(2)利用数据相关的复杂性测度(CMD),得到了网络规模的泛化误差界不变量。从这个CMD界可以得出,网络可以推广任意光滑函数。(3)一个简单的和解析的核函数被推导出来,实际上相当于一个完全训练的网络。该内核在少样本学习方面优于其相应的网络和现有的黄金标准随机森林。为了保持所有这些结果,网络比例因子$κ$应相对于时间减小。样本量然而,在这种情况下,减少$κ$,我们证明,上述结果是令人惊讶的错误。这是因为当$κ$相对于时间减小时,训练好的网络输出值减小为零。n.为了解决这个问题,我们通过从本质上删除受$κ$影响的值来收紧密钥边界。我们更严格的分析解决了缩放问题,并使原始NTK为基础的结果的验证。

英文摘要:

Recent theoretical works based on the neural tangent kernel (NTK) have shed light on the optimization and generalization of over-parameterized networks, and partially bridge the gap between their practical success and classical learning theory. Especially, using the NTK-based approach, the following three representative results were obtained: (1) A training error bound was derived to show that networks can fit any finite training sample perfectly by reflecting a tighter characterization of training speed depending on the data complexity. (2) A generalization error bound invariant of network size was derived by using a data-dependent complexity measure (CMD). It follows from this CMD bound that networks can generalize arbitrary smooth functions. (3) A simple and analytic kernel function was derived as indeed equivalent to a fully-trained network. This kernel outperforms its corresponding network and the existing gold standard, Random Forests, in few shot learning. For all of these results to hold, the network scaling factor $κ$ should decrease w.r.t. sample size n. In this case of decreasing $κ$, however, we prove that the aforementioned results are surprisingly erroneous. It is because the output value of trained network decreases to zero when $κ$ decreases w.r.t. n. To solve this problem, we tighten key bounds by essentially removing $κ$-affected values. Our tighter analysis resolves the scaling problem and enables the validation of the original NTK-based results.

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。

↑