Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search

Neural architecture search (NAS) automates the design of deep neural networks. One of the main challenges in searching complex and noncontinuous architectures is to compare the similarity of networks that the conventional Euclidean metric may fail to capture. Optimal transport (OT) is resilient to such complex structure by considering the minimal cost for transporting a network into another. However, the OT is generally not negative definite which may limit its ability to build the positive-definite kernels required in many kernel-dependent frameworks. Building upon tree-Wasserstein (TW), which is a negative definite variant of OT, we develop a novel discrepancy for neural architectures, and demonstrate it within a Gaussian process (GP) surrogate model for the sequential NAS settings. Furthermore, we derive a novel parallel NAS, using quality kdeterminantal point process on the GP posterior, to select diverse and high-performing architectures from a discrete set of candidates. We empirically demonstrate that our TW-based approaches outperform other baselines in both sequential and parallel NAS.