Fast MNAS: Uncertainty-aware Neural Architecture Search with Lifelong Learning

1 Jan 2021 Anonymous

Sampling-based neural architecture search (NAS) always guarantees better convergence yet suffers from huge computational resources compared with gradient-based approaches, due to the rollout bottleneck -- exhaustive training for each sampled generation on proxy tasks. This work provides a general pipeline to accelerate the convergence of the rollout process as well as the RL learning process in sampling-based NAS... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper

Entropy Regularization
Policy Gradient Methods