In the past decade, advances in deep learning have resulted in breakthroughs in a variety of
areas, including computer vision, natural language understanding, speech recognition, and …

Abstract Neural Architecture Search (NAS) often trains and evaluates a large number of
architectures. Recent predictor-based NAS approaches attempt to alleviate such heavy …

Time-consuming performance evaluation is the bottleneck of traditional Neural Architecture
Search (NAS) methods. Predictor-based NAS can speed up performance evaluation by …

While early research in neural architecture search (NAS) required extreme computational
resources, the recent releases of tabular and surrogate benchmarks have greatly increased …

Neural architecture search (NAS) has seen a steep rise in interest over the last few years.
Many algorithms for NAS consist of searching through a space of architectures by iteratively …

The success of a specific neural network architecture is closely tied to the dataset and task it
tackles; there is no one-size-fits-all solution. Thus considerable efforts have been made to …

Performance estimation of neural architecture is a crucial component of neural architecture
search (NAS). Meanwhile, neural predictor is a current mainstream performance estimation …

Optimization of directed acyclic graph (DAG) structures has many applications, such as
neural architecture search (NAS) and probabilistic graphical model learning. Encoding …

Existing NAS methods suffer from either an excessive amount of time for repetitive sampling
and training of many task-irrelevant architectures. To tackle such limitations of existing NAS …

Efficient deployment of neural networks (NN) requires the co-optimization of accuracy and
latency. For example, hardware-aware neural architecture search has been used to …