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 2110.09548cs.LGcs.AIstat.ML
收藏

路径正则化:一种用于并行 ReLU 网络的凸性与稀疏性诱导正则化

Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks

Stanford University(斯坦福大学)

Tolga Ergen, Mert Pilanci

AI总结:

本文研究并行 ReLU 网络的训练问题,提出路径正则化以揭示隐藏凸性并诱导群稀疏,同时给出全多项式时间近似算法及全局最优性保证。

摘要:

理解深度神经网络成功背后的基本原理是当前文献中最重要的开放问题之一。为此,我们研究深度神经网络的训练问题,并引入一种解析方法来揭示优化景观中隐藏的凸性。我们考虑一种深度并行 ReLU 网络架构,该架构也将标准深度网络和 ResNets 包含为其特例。随后,我们证明逐路径正则化的训练问题可以表示为一个精确的凸优化问题。我们进一步证明,等价的凸问题通过一种群稀疏性诱导范数得到正则化。因此,经过路径正则化的并行 ReLU 网络可被视为高维空间中的一种简约凸模型。更重要的是,由于原始训练问题可能无法在多项式时间内训练,我们提出一种在所有数据维度上均具有完全多项式时间复杂度的近似算法。接着,我们证明了该算法的强全局最优性保证。我们还提供了支持我们理论的实验。

英文摘要:

Understanding the fundamental principles behind the success of deep neural networks is one of the most important open questions in the current literature. To this end, we study the training problem of deep neural networks and introduce an analytic approach to unveil hidden convexity in the optimization landscape. We consider a deep parallel ReLU network architecture, which also includes standard deep networks and ResNets as its special cases. We then show that pathwise regularized training problems can be represented as an exact convex optimization problem. We further prove that the equivalent convex problem is regularized via a group sparsity inducing norm. Thus, a path regularized parallel ReLU network can be viewed as a parsimonious convex model in high dimensions. More importantly, since the original training problem may not be trainable in polynomial-time, we propose an approximate algorithm with a fully polynomial-time complexity in all data dimensions. Then, we prove strong global optimality guarantees for this algorithm. We also provide experiments corroborating our theory.

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。

↑