We actually compare with AutoGrow in2 paragraph Growing Wider and Deeper Networks, around line 218. Due to the space limit, we move the re-3 sult to appendix. Moreover, AutoGrow can only grow layers so it does not compare with many well known4 NAS baseline. We choose DARTS because it is still a very popular baseline in recent NAS papers, which5 gives new papers a fast, gradient based, weight-sharing NAS baseline with a low error rate to compare with.6 RSPSDARTSV1/2 ENASSETNGDASOurs Acc. At least it can be validated on9 NAS-Bench-101,201.

Thus,DASH' scross-s space classification ver, space lar ficienccomputational considered DAS multi-scale volutions, thevolutions, with outputs.

However,this assumption may not hold.