We develop an analytical framework to characterize the set of optimal ReLU
neural networks by reformulating the non-convex training problem as a convex
program. We show that the global optima of the convex parameterization are
given by a polyhedral set and then extend this characterization to the optimal
set of the non-convex training objective. Since all stationary points of the
ReLU training problem can be represented as optima of sub-sampled convex
programs, our work provides a general expression for all critical points of the
non-convex objective. We then leverage our results to provide an optimal
pruning algorithm for computing minimal networks, establish conditions for the
regularization path of ReLU networks to be continuous, and develop sensitivity
results for minimal ReLU networks.

通过把非凸培训问题重新定义为凸程序，我们开发了一个分析框架来表征最佳 ReLU 神经网络的集合，并指出凸参数化的全局最优解是由一个多面体集合给出的。我们还扩展了这种特征，以获得非凸培训目标的最优集合。由于 ReLU 培训问题的所有静态点都可以表示为子采样凸计划的最优解，因此我们的工作为所有非凸目标的临界点提供了一个一般表达式。我们利用这些结果，提供了一种计算最小网络的最佳减枝算法，建立了 ReLU 网络正则化路径连续的条件，并开发了最小 ReLU 网络的灵敏度结果。