Bag of Tricks for Neural Architecture Search
This work tackles the problem of unreliable neural architecture search for researchers and practitioners, but it appears incremental as it focuses on practical tricks rather than a new paradigm.
The paper addresses the instability and sensitivity of neural architecture search methods by discussing practical considerations to improve their stability, efficiency, and performance, though no concrete numbers are provided.
While neural architecture search methods have been successful in previous years and led to new state-of-the-art performance on various problems, they have also been criticized for being unstable, being highly sensitive with respect to their hyperparameters, and often not performing better than random search. To shed some light on this issue, we discuss some practical considerations that help improve the stability, efficiency and overall performance.