Start: April 11, 2022, 6 p.m.
Description: Code your own Zero-Cost predictor and see how well it performs on an unseen dataset. This dataset consists of models sampled from search spaces available in NASLib and trained on new datasets. It serves only as a proxy for the final performance. The final performance is evaluated using other unseen benchmarks.
July 8, 2022, 11:59 p.m.
You must be logged in to participate in competitions.
Sign In