Random Search and Reproducibility for Neural Architecture Search — mentioned by williamsmj

Fri, 01 Mar 2019 16:49:19 GMT

I'd be interested in the creator's thoughts on this paper, "Random Search and Reproducibility for Neural Architecture Search", https://arxiv.org/abs/1902.07638, posted on the arxiv last week. Among other conclusions, they find: "Our results show that random search with early-stopping is a competitive NAS baseline, e.g., it performs at least as well as ENAS, a leading NAS method, on both benchmarks" ENAS, the specific algorithm that they find does no better than chance, is in this library. My understanding is that the results are pretty generic though, i.e. NAS is very far from a solved…

Paper and discussion history. A mention is not an endorsement.

Random Search and Reproducibility for Neural Architecture Search — HN submission

Fri, 22 Feb 2019 15:11:26 GMT

Random Search and Reproducibility for Neural Architecture Search

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Random Search and Reproducibility for Neural Architecture Search · HackerPapers discussions

Random Search and Reproducibility for Neural Architecture Search — mentioned by williamsmj

Random Search and Reproducibility for Neural Architecture Search — HN submission