Skip to content
This repository was archived by the owner on Oct 31, 2023. It is now read-only.

Releases: facebookresearch/LaMCTS

version 0.1

18 Oct 00:49
@linnanwang linnanwang
0.1
205fa7b
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
version 0.1 Pre-release
Pre-release

Evaluation on NASBench-101 : Evaluating LaNAS on NASBench-101 without training models.

Our Searched Models, LaNet: SoTA results: • 99.03% on CIFAR-10 • 77.7% @ 240MFLOPS on ImageNet.

One/Few-shot LaNAS: Using a supernet to evaluate the model, obtaining results within a few GPU days.

Distributed LaNAS: Distributed framework for LaNAS, usable with hundreds of GPUs.

Training heuristics used: We list all tricks used in ImageNet training to reach SoTA.

Performance with baselines: 1 minute evaluations of LA-MCTS v.s. Bayesian Optimization and Evolutionary Search.

Mujoco Experiments: LA-MCTS on Mujoco environment.

Loading