mlsanityData to 14 Oct 2026

L2NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning

arXiv 2109.12425 ↗First posted 25 Sep 2021cs.LG cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Neural architecture search (NAS) has achieved remarkable results in deep neural network design. Differentiable architecture search converts the search over discrete architectures into a hyperparameter optimization problem which can be solved by gradient descent. However, questions have been raised regarding the effectiveness and generalizability of gradient methods for solving non-convex architecture hyperparameter optimization problems. In this paper, we propose L2NAS, which learns to intelligently optimize and update architecture hyperparameters via an actor neural network based on the distribution of high-performing architectures in the search history. We introduce a quantile-driven training procedure which efficiently trains L2NAS in an actor-critic framework via continuous-action reinforcement learning. Experiments show that L2NAS achieves state-of-the-art results on NAS-Bench-201 benchmark as well as DARTS search space and Once-for-All MobileNetV3 search space. We also show that search policies generated by L2NAS are generalizable and transferable across different training datasets with minimal fine-tuning.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 38 of its 46 references that are in the map. First posted on arXiv 25 Sep 2021.

Builds on

38 of 46 references.

References · 38

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  5. 2015Continuous control with deep reinforcement learningcited by 3,407
  6. 2019Searching for MobileNetV3cited by 1,994
  7. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  8. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  9. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  10. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  11. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  12. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
26 more
  1. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
  2. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 416
  3. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
  4. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 377
  5. 2018SNAS: Stochastic Neural Architecture Searchcited by 289
  6. 2019PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Searchcited by 265
  7. 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 260
  8. 2019Random Search and Reproducibility for Neural Architecture Searchcited by 254
  9. 2017The Marginal Value of Adaptive Gradient Methods in Machine Learningcited by 250
  10. 2019Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluationcited by 230
  11. 2018Neural Architecture Search with Bayesian Optimisation and Optimal Transportcited by 195
  12. 2019Understanding and Robustifying Differentiable Architecture Searchcited by 178
  13. 2019Evaluating the Search Phase of Neural Architecture Searchcited by 120
  14. 2020Stabilizing Differentiable Architecture Search via Perturbation-based Regularizationcited by 102
  15. 2020GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learningcited by 89
  16. 2020Can weight sharing outperform random architecture search? An investigation with TuNAScited by 68
  17. 2020EcoNAS: Finding Proxies for Economical Neural Architecture Searchcited by 61
  18. 2020Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?cited by 59
  19. 2020MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulationcited by 57
  20. 2020Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gapcited by 50
  21. 2019Understanding Architectures Learnt by Cell-based Neural Architecture Searchcited by 48
  22. 2020Geometry-Aware Gradient Algorithms for Neural Architecture Searchcited by 40
  23. 2020ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Codingcited by 36
  24. 2018Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Searchcited by 18
  25. 2019Multinomial Distribution Learning for Effective Neural Architecture Searchcited by 17
  26. 2016Learning to Learn without Gradient Descent by Gradient Descentcited by 9

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 0; 2024: 0; 2025: 2.

6 papers.

  1. 2022AIO-P: Expanding Neural Performance Predictors Beyond Image Classificationcited by 8
  2. 2022GENNAPE: Towards Generalized Neural Architecture Performance Estimatorscited by 5
  3. 2022Multi-Agent Automated Machine Learningcited by 3
  4. 2025Dextr: Zero-Shot Neural Architecture Search with Singular Value Decomposition and Extrinsic Curvaturecited by 1
  5. 2022GraTO: Graph Neural Network Framework Tackling Over-smoothing with Neural Architecture Searchcited by 0
  6. 2025An Integrated Approach to Neural Architecture Search for Deep Q-Networkscited by 0