Differentiable Architecture Search (DARTS) is an effective continuous relaxation-based network architecture search (NAS) method with low search cost. It has attracted significant attentions in Auto-ML research and becomes one of the most useful paradigms in NAS. Although DARTS can produce superior efficiency over traditional NAS approaches with better control of complex parameters, oftentimes it suffers from stabilization issues in producing deteriorating architectures when discretizing the continuous architecture. We observed considerable loss of validity causing dramatic decline in performance at this final discretization step of DARTS. To address this issue, we propose a Mean-Shift based DARTS (MS-DARTS) to improve stability based on sampling and perturbation. Our approach can improve bot the stability and accuracy of DARTS, by smoothing the loss landscape and sampling architecture parameters within a suitable bandwidth. We investigate the convergence of our mean-shift approach, together with the effects of bandwidth selection that affects stability and accuracy. Evaluations performed on CIFAR-10, CIFAR-100, and ImageNet show that MS-DARTS archives higher performance over other state-of-the-art NAS methods with reduced search cost.

翻译：可区别建筑搜索(DARTS)是一种有效的、持续放松的网络建筑搜索(NAS)方法,其搜索成本低,在自动-ML研究中引起极大关注,并成为NAS中最有用的范例之一。虽然DARTS能够比传统的NAS方法产生更高的效率,更好地控制复杂的参数,但在连续建筑分解时,在生成恶化的建筑方面往往会遇到稳定问题。我们观察到,在DARTS的这一最后分解步骤中,由于有效性的丧失,导致性能急剧下降。为了解决这一问题,我们提议采用以平均-希夫为基础的DARTS(MS-DARSS),以基于取样和扰动的稳定性为基础,改进DARTS的稳定性和准确性。我们的方法可以通过在合适的带宽度范围内平滑损失景观和取样结构参数来提高DARTS的稳定性和准确性。我们调查我们的中位方法的趋同,以及影响稳定性和准确性的带宽度选择的影响。对CIFAR-10、CIFAR-100和图像Net进行的评估表明,MS-DARS档案比其他州-艺术NAS方法的更高性,并降低搜索成本。