Robustifying and Boosting Training-Free Neural Architecture Search

arXiv:2403.07591v1 Announce Type: new
Abstract: Neural architecture search (NAS) has become a key component of AutoML and a standard tool to automate the design of deep neural networks. Recently, training-free NAS as an emerging paradigm has successfully reduced the search costs of standard training-based NAS by estimating the true architecture performance with only training-free metrics. Nevertheless, the estimation ability of these metrics typically varies across different tasks, making it challenging to achieve robust and consistently good search performance on diverse …

abstract architecture arxiv automate automl become boosting costs cs.lg design free key nas networks neural architecture search neural networks paradigm performance search standard tool training true type