DARTS: Differentiable Architecture Search

Hanxiao LiuKaren SimonyanYiming Yang

   Papers with code   Abstract  PDF

This paper addresses the scalability challenge of architecture search by formulating the task in a differentiable manner. Unlike conventional approaches of applying evolution or reinforcement learning over a discrete and non-differentiable search space, our method is based on the continuous relaxation of the architecture representation, allowing efficient search of the architecture using gradient descent... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD