SCARLET-NAS

2000년 도입 · 논문 1편에서 사용

SCARLET-NAS is a type of neural architecture search that utilises a learnable stabilizer to calibrate feature deviation, named the Equivariant Learnable Stabilizer (ELS). Previous one-shot approaches can be limited by fixed-depth search spaces. With SCARLET-NAS, we use the equivariant learnable stabilizer on each skip connection. This can lead to improved convergence, more reliable evaluation, and retained equivalence. The third benefit is deemed most important by the authors for scalability.

출처: SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search

소개 논문: SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search