# Noisy Differentiable Architecture Search

arXiv: https://arxiv.org/abs/2005.03566 · HTML: https://mlsanity.com/paper/2005.03566/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2020.

## Built on by (most cited first, 16 of 16)

- [KNAS: Green Neural Architecture Search](https://mlsanity.com/paper/2111.13293/) (2021)
- [On Redundancy and Diversity in Cell-based Neural Architecture Search](https://mlsanity.com/paper/2203.08887/) (2022)
- [Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecycle](https://mlsanity.com/paper/2303.01980/) (2023)
- [Reconsidering CO2 emissions from Computer Vision](https://mlsanity.com/paper/2104.08702/) (2021)
- [β-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search](https://mlsanity.com/paper/2301.06393/) (2023)
- [Learning from Mistakes -- A Framework for Neural Architecture Search](https://mlsanity.com/paper/2111.06353/) (2021)
- [Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search](https://mlsanity.com/paper/2304.05405/) (2023)
- [Encoder-Decoder Neural Architecture Optimization for Keyword Spotting](https://mlsanity.com/paper/2106.02738/) (2021)
- [CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks](https://mlsanity.com/paper/2211.05950/) (2022)
- [Efficient Architecture Search via Bi-level Data Pruning](https://mlsanity.com/paper/2312.14200/) (2023)
- [A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism](https://mlsanity.com/paper/2407.15600/) (2024)
- [Unchain the Search Space with Hierarchical Differentiable Architecture Search](https://mlsanity.com/paper/2101.04028/) (2021)
- [Learning from Mistakes based on Class Weighting with Application to Neural Architecture Search](https://mlsanity.com/paper/2112.00275/) (2021)
- [Path-Adaptive Matting for Efficient Inference Under Various Computational Cost Constraints](https://mlsanity.com/paper/2503.03228/) (2025)
- [FX-DARTS: Designing Topology-unconstrained Architectures with Differentiable Architecture Search and Entropy-based Super-network Shrinking](https://mlsanity.com/paper/2504.20079/) (2025)
- [PCOV-KWS: Multi-task Learning for Personalized Customizable Open Vocabulary Keyword Spotting](https://mlsanity.com/paper/2603.18023/) (2026)

## Abstract (arXiv)

Simplicity is the ultimate sophistication. Differentiable Architecture Search (DARTS) has now become one of the mainstream paradigms of neural architecture search. However, it largely suffers from the well-known performance collapse issue due to the aggregation of skip connections. It is thought to have overly benefited from the residual structure which accelerates the information flow. To weaken this impact, we propose to inject unbiased random noise to impede the flow. We name this novel approach NoisyDARTS. In effect, a network optimizer should perceive this difficulty at each training step and refrain from overshooting, especially on skip connections. In the long run, since we add no bias to the gradient in terms of expectation, it is still likely to converge to the right solution area. We also prove that the injected noise plays a role in smoothing the loss landscape, which makes the optimization easier. Our method features extreme simplicity and acts as a new strong baseline. We perform extensive experiments across various search spaces, datasets, and tasks, where we robustly achieve state-of-the-art results. Our code is available at https://github.com/xiaomi-automl/NoisyDARTS.