# ZARTS: On Zero-order Optimization for Neural Architecture Search

arXiv: https://arxiv.org/abs/2110.04743 · HTML: https://mlsanity.com/paper/2110.04743/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 50 references that are in the map.
- First posted on arXiv 10 Oct 2021.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Black-box Adversarial Attacks with Limited Queries and Information](https://mlsanity.com/paper/1804.08598/) (2018)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [SNAS: Stochastic Neural Architecture Search](https://mlsanity.com/paper/1812.09926/) (2018)
- [PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search](https://mlsanity.com/paper/1907.05737/) (2019)
- [Searching for A Robust Neural Architecture in Four GPU Hours](https://mlsanity.com/paper/1910.04465/) (2019)
- [Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation](https://mlsanity.com/paper/1904.12760/) (2019)
- [Understanding and Robustifying Differentiable Architecture Search](https://mlsanity.com/paper/1909.09656/) (2019)
- [A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning](https://mlsanity.com/paper/2006.06224/) (2020)
- [Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search](https://mlsanity.com/paper/1911.12126/) (2019)
- [Evaluating the Search Phase of Neural Architecture Search](https://mlsanity.com/paper/1902.08142/) (2019)
- [Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization](https://mlsanity.com/paper/1805.10367/) (2018)
- [Stabilizing Differentiable Architecture Search via Perturbation-based Regularization](https://mlsanity.com/paper/2002.05283/) (2020)
- [Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources](https://mlsanity.com/paper/2007.08714/) (2020)
- [DARTS-: Robustly Stepping out of Performance Collapse Without Indicators](https://mlsanity.com/paper/2009.01027/) (2020)
- [SGAS: Sequential Greedy Architecture Search](https://mlsanity.com/paper/1912.00195/) (2019)
- [A Theoretical and Empirical Comparison of Gradient Approximations in Derivative-Free Optimization](https://mlsanity.com/paper/1905.01332/) (2019)
- [ES-MAML: Simple Hessian-Free Meta Learning](https://mlsanity.com/paper/1910.01215/) (2019)
- [An ADMM Based Framework for AutoML Pipeline Configuration](https://mlsanity.com/paper/1905.00424/) (2019)
- [Gradientless Descent: High-Dimensional Zeroth-Order Optimization](https://mlsanity.com/paper/1911.06317/) (2019)
- [ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding](https://mlsanity.com/paper/2010.06176/) (2020)

## Built on by (most cited first, 18 of 18)

- [DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training](https://mlsanity.com/paper/2310.02025/) (2023)
- [Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning](https://mlsanity.com/paper/2402.15751/) (2024)
- [Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures](https://mlsanity.com/paper/2410.07698/) (2024)
- [On Finding Small Hyper-Gradients in Bilevel Optimization: Hardness Results and Improved Analysis](https://mlsanity.com/paper/2301.00712/) (2023)
- [Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning](https://mlsanity.com/paper/2502.03304/) (2025)
- [Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles](https://mlsanity.com/paper/2306.14853/) (2023)
- [Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity](https://mlsanity.com/paper/2405.19697/) (2024)
- [Perturbation-efficient Zeroth-order Optimization for Hardware-friendly On-device Training](https://mlsanity.com/paper/2504.20314/) (2025)
- [PA&DA: Jointly Sampling PAth and DAta for Consistent NAS](https://mlsanity.com/paper/2302.14772/) (2023)
- [Fully Zeroth-Order Bilevel Programming via Gaussian Smoothing](https://mlsanity.com/paper/2404.00158/) (2024)
- [ElasticZO: A Memory-Efficient On-Device Learning with Combined Zeroth- and First-Order Optimization](https://mlsanity.com/paper/2501.04287/) (2025)
- [LancBiO: dynamic Lanczos-aided bilevel optimization via Krylov subspace](https://mlsanity.com/paper/2404.03331/) (2024)
- [Differentiable Arbitrating in Zero-sum Markov Games](https://mlsanity.com/paper/2302.10058/) (2023)
- [Accelerated Fully First-Order Methods for Bilevel and Minimax Optimization](https://mlsanity.com/paper/2405.00914/) (2024)
- [Riemannian Bilevel Optimization](https://mlsanity.com/paper/2405.15816/) (2024)
- [Dense Optimizer : An Information Entropy-Guided Structural Search Method for Dense-like Neural Network Design](https://mlsanity.com/paper/2410.07499/) (2024)
- [Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptation](https://mlsanity.com/paper/2608.12279/) (2026)
- [StructZO: Structured Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning](https://mlsanity.com/paper/2610.16451/) (2026)

## Abstract (arXiv)

Differentiable architecture search (DARTS) has been a popular one-shot paradigm for NAS due to its high efficiency. It introduces trainable architecture parameters to represent the importance of candidate operations and proposes first/second-order approximation to estimate their gradients, making it possible to solve NAS by gradient descent algorithm. However, our in-depth empirical results show that the approximation will often distort the loss landscape, leading to the biased objective to optimize and in turn inaccurate gradient estimation for architecture parameters. This work turns to zero-order optimization and proposes a novel NAS scheme, called ZARTS, to search without enforcing the above approximation. Specifically, three representative zero-order optimization methods are introduced: RS, MGS, and GLD, among which MGS performs best by balancing the accuracy and speed. Moreover, we explore the connections between RS/MGS and gradient descent algorithm and show that our ZARTS can be seen as a robust gradient-free counterpart to DARTS. Extensive experiments on multiple datasets and search spaces show the remarkable performance of our method. In particular, results on 12 benchmarks verify the outstanding robustness of ZARTS, where the performance of DARTS collapses due to its known instability issue. Also, we search on the search space of DARTS to compare with peer methods, and our discovered architecture achieves 97.54% accuracy on CIFAR-10 and 75.7% top-1 accuracy on ImageNet, which are state-of-the-art performance.