mlsanityData to 7 Oct 2026

LayerNAS: Neural Architecture Search in Polynomial Complexity

arXiv 2304.11517 ↗First posted 23 Apr 2023cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Neural Architecture Search (NAS) has become a popular method for discovering effective model architectures, especially for target hardware. As such, NAS methods that find optimal architectures under constraints are essential. In our paper, we propose LayerNAS to address the challenge of multi-objective NAS by transforming it into a combinatorial optimization problem, which effectively constrains the search complexity to be polynomial. For a model architecture with L layers, we perform layerwise-search for each layer, selecting from a set of search options mathbbS. LayerNAS groups model candidates based on one objective, such as model size or latency, and searches for the optimal model based on another objective, thereby splitting the cost and reward elements of the search. This approach limits the search complexity to O(H · |mathbbS| · L) , where H is a constant set in LayerNAS. Our experiments show that LayerNAS is able to consistently discover superior models across a variety of search spaces in comparison to strong baselines, including search spaces derived from NATS-Bench, MobileNetV2 and MobileNetV3.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 36 of its 44 references that are in the map. First posted on arXiv 23 Apr 2023.

Builds on

36 of 44 references.

References · 36

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2019Searching for MobileNetV3cited by 1,984
  6. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  7. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  8. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  9. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  10. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  11. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  12. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
24 more
  1. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  2. 2017Progressive Neural Architecture Searchcited by 483
  3. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  4. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 466
  5. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  6. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 375
  7. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 374
  8. 2019NAS-Bench-101: Towards Reproducible Neural Architecture Searchcited by 340
  9. 2020Neural Architecture Search without Trainingcited by 241
  10. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  11. 2018Neural Architecture Search with Bayesian Optimisation and Optimal Transportcited by 192
  12. 2018Efficient Multi-objective Neural Architecture Search via Lamarckian Evolutioncited by 151
  13. 2020A Survey on Evolutionary Neural Architecture Searchcited by 142
  14. 2019FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Searchcited by 129
  15. 2020NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Sizecited by 98
  16. 2020GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernetcited by 69
  17. 2020Can weight sharing outperform random architecture search? An investigation with TuNAScited by 68
  18. 2019BayesNAS: A Bayesian Approach for Neural Architecture Searchcited by 67
  19. 2021KNAS: Green Neural Architecture Searchcited by 33
  20. 2021NASI: Label- and Data-agnostic Neural Architecture Search at Initializationcited by 28
  21. 2022Shapley-NAS: Discovering Operation Contribution for Neural Architecture Searchcited by 23
  22. 2021Analyzing and Mitigating Interference in Neural Architecture Searchcited by 20
  23. 2021Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generatorcited by 15
  24. 2022Generalization Properties of NAS under Activation and Skip Connection Searchcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 0; 2026: 1.

3 papers.

  1. 2023MathNAS: If Blocks Have a Role in Mathematical Architecture Designcited by 4
  2. 2023DONNAv2 -- Lightweight Neural Architecture Search for Vision taskscited by 0
  3. 2026MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Modelscited by 0