Reviews NAS methods through bilevel optimization lens, categorizing them into sampling-based and theory-based, and proposes an auxiliary math programming framework for more principled architecture and weight updates.
Autorl hyperparameter landscapes.arXiv preprint arXiv:2304.02396, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bilevel Optimization for Neural Architecture Search
Reviews NAS methods through bilevel optimization lens, categorizing them into sampling-based and theory-based, and proposes an auxiliary math programming framework for more principled architecture and weight updates.