Pith. sign in

REVIEW

Analyzing the Expected Hitting Time of Evolutionary Computation-based Neural Architecture Search Algorithms

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 2210.05397 v3 pith:VXDJA4HL submitted 2022-10-11 cs.NE

Analyzing the Expected Hitting Time of Evolutionary Computation-based Neural Architecture Search Algorithms

classification cs.NE
keywords enasalgorithmstimearchitecturehittingmethodneuralsearch
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Evolutionary computation-based neural architecture search (ENAS) is a popular technique for automating architecture design of deep neural networks. Despite its groundbreaking applications, there is no theoretical study for ENAS. The expected hitting time (EHT) is one of the most important theoretical issues, since it implies the average computational time complexity. This paper proposes a general method by integrating theory and experiment for estimating the EHT of ENAS algorithms, which includes common configuration, search space partition, transition probability estimation, population distribution fitting, and hitting time analysis. By exploiting the proposed method, we consider the ($\lambda$+$\lambda$)-ENAS algorithms with different mutation operators and estimate the lower bounds of the EHT. Furthermore, we study the EHT on the NAS-Bench-101 problem, and the results demonstrate the validity of the proposed method. To the best of our knowledge, this work is the first attempt to establish a theoretical foundation for ENAS algorithms.

discussion (0)

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