Weighted losses identify top architectures best with enough training data, ranking losses win with very few data, and switching between them (PWLNAS) gives small consistent gains in predictor-based NAS.
Nas-bench-201: Extending the scope of reproducible neural architecture search
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Loss Functions for Predictor-based Neural Architecture Search
Weighted losses identify top architectures best with enough training data, ranking losses win with very few data, and switching between them (PWLNAS) gives small consistent gains in predictor-based NAS.