Pith. sign in

REVIEW 1 cited by

Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters

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 1910.11831 v5 pith:UUOA3Z5Z submitted 2019-10-25 cs.LG cs.CVstat.ML

classification cs.LGcs.CVstat.ML
keywords searchestimationarchitecturaldartsgradientsamendedapproachmethod
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

DARTS is a popular algorithm for neural architecture search (NAS). Despite its great advantage in search efficiency, DARTS often suffers weak stability, which reflects in the large variation among individual trials as well as the sensitivity to the hyper-parameters of the search process. This paper owes such instability to an optimization gap between the super-network and its sub-networks, namely, improving the validation accuracy of the super-network does not necessarily lead to a higher expectation on the performance of the sampled sub-networks. Then, we point out that the gap is due to the inaccurate estimation of the architectural gradients, based on which we propose an amended estimation method. Mathematically, our method guarantees a bounded error from the true gradients while the original estimation does not. Our approach bridges the gap from two aspects, namely, amending the estimation on the architectural gradients, and unifying the hyper-parameter settings in the search and re-training stages. Experiments on CIFAR10 and ImageNet demonstrate that our approach largely improves search stability and, more importantly, enables DARTS-based approaches to explore much larger search spaces that have not been investigated before.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. confopt: A Library for Implementation and Evaluation of Gradient-based One-Shot NAS Methods

    cs.LG 2025-07 conditional novelty 5.0 of 10

    A library and nine DARTS-derived benchmarks show that relative rankings of gradient-based one-shot NAS methods are unstable, making DARTS-only evaluation unreliable.

Pith tools