Dropout-based regularization methods can be regarded as injecting random noise with pre-defined magnitude to different parts of the neural network during training. It was recently shown that Bayesian dropout procedure not only improves generalization but also leads to extremely sparse neural architectures by automatically setting the individual noise magnitude per weight. However, this sparsity can hardly be used for acceleration since it is unstructured. In the paper, we propose a new Bayesian model that takes into account the computational structure of neural networks and provides structured sparsity, e.g.

Recent neural architecture search (NAS) frameworks have been successful in finding optimal architectures for given conditions (e.g., performance or latency).

Graph structured data are abundant in the real world.

( , 0)

Now,we describe the latencymeasurement pipeline for desktop GPUs, Jetson, serverCPUs, and mobile phone. Furthermore, evenwith the same GPU device, the correlation scores are not high ifthebatch sizes are different. Figure A.1: Visualization of 10 reference neural architectures we used for NAS-Bench-201 search space. Werandomlyselected10reference architectures for each search space (NAS-Bench-201, FBNet, and MobileNetV3) and used them across all experiments and devices of the same search space. In Figure A.1, we visualize 10 reference architectures that we used in NAS-Bench-201 search space.

Most existing neural architecture search (NAS) algorithms are dedicated to and evaluated bythedownstream tasks, e.g.,image classification incomputer vision.