Pith. sign in

REVIEW

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2107.03719 v1 pith:LKHB6EIG submitted 2021-07-08 cs.LG cs.AIstat.ML

Bag of Tricks for Neural Architecture Search

classification cs.LG cs.AIstat.ML
keywords searcharchitecturebeenneuralperformancesomebetterconsiderations
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

While neural architecture search methods have been successful in previous years and led to new state-of-the-art performance on various problems, they have also been criticized for being unstable, being highly sensitive with respect to their hyperparameters, and often not performing better than random search. To shed some light on this issue, we discuss some practical considerations that help improve the stability, efficiency and overall performance.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.