arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.14798cs.LGcs.CCstat.ML
收藏

CNN结构的隐式凸正则化器:多项式时间内二层和三层网络的凸优化

Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time

Stanford University(斯坦福大学)

Tolga Ergen, Mert Pilanci

摘要:

我们研究了使用ReLU激活的卷积神经网络(CNN)的训练,并引入了精确的凸优化公式,该公式具有关于数据样本数量,神经元数量和数据维度的多项式复杂度。更具体地说,我们开发了一个凸分析框架,利用半无限对偶,以获得几个两层和三层CNN架构的等价凸优化问题。我们首先证明了两层CNN可以通过$\ell_2$范数正则化凸规划进行全局优化。然后,我们证明了具有单个ReLU层的多层循环CNN训练问题等价于$\ell_1$正则化凸程序,该程序鼓励谱域中的稀疏性。我们还将这些结果扩展到具有两个ReLU层的三层CNN。此外,我们提出了我们的方法扩展到不同的池化方法,这阐明了隐含的建筑偏见凸正则化。

英文摘要:

We study training of Convolutional Neural Networks (CNNs) with ReLU activations and introduce exact convex optimization formulations with a polynomial complexity with respect to the number of data samples, the number of neurons, and data dimension. More specifically, we develop a convex analytic framework utilizing semi-infinite duality to obtain equivalent convex optimization problems for several two- and three-layer CNN architectures. We first prove that two-layer CNNs can be globally optimized via an $\ell_2$ norm regularized convex program. We then show that multi-layer circular CNN training problems with a single ReLU layer are equivalent to an $\ell_1$ regularized convex program that encourages sparsity in the spectral domain. We also extend these results to three-layer CNNs with two ReLU layers. Furthermore, we present extensions of our approach to different pooling methods, which elucidates the implicit architectural bias as convex regularizers.

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。

↑