mlsanityData to 14 Oct 2026

Neural Architecture Search with Reinforcement Learning

arXiv 1611.01578 ↗First posted 5 Nov 2016cs.LG cs.AI cs.NEcited by 1,499

Not on the map. Why?

Cited by 31 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a recurrent network to generate the model descriptions of neural networks and train this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set. On the CIFAR-10 dataset, our method, starting from scratch, can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy. Our CIFAR-10 model achieves a test error rate of 3.65, which is 0.09 percent better and 1.05x faster than the previous state-of-the-art model that used a similar architectural scheme. On the Penn Treebank dataset, our model can compose a novel recurrent cell that outperforms the widely-used LSTM cell, and other state-of-the-art baselines. Our cell achieves a test set perplexity of 62.4 on the Penn Treebank, which is 3.6 perplexity better than the previous state-of-the-art model. The cell can also be transferred to the character language modeling task on PTB and achieves a state-of-the-art perplexity of 1.214.

Key facts. Cited by 1,499 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2017: 1; 2018: 2; 2019: 1; 2020: 0; 2021: 450; 2022: 337; 2023: 227; 2024: 199; 2025: 148; 2026: 134.

1,499 papers.

Sort:

By area:

  1. 2024VMamba: Visual State Space Modelcited by 969
  2. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  3. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 674
  4. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 522
  5. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  6. 2023Symbolic Discovery of Optimization Algorithmscited by 434
  7. 2021Dynamic Neural Networks: A Surveycited by 408
  8. 2023DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretrainingcited by 399
  9. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 372
  10. 2021True Few-Shot Learning with Language Modelscited by 344
  11. 2023A Survey on Model Compression for Large Language Modelscited by 269
  12. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
38 more
  1. 2025AIDE: AI-Driven Exploration in the Space of Codecited by 226
  2. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  3. 2024MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Casescited by 223
  4. 2024A Survey on Efficient Inference for Large Language Modelscited by 205
  5. 2021Zero-Cost Proxies for Lightweight NAScited by 199
  6. 2023OpenAGI: When LLM Meets Domain Expertscited by 197
  7. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  8. 2021AutoFormer: Searching Transformers for Visual Recognitioncited by 188
  9. 2022Dataset Condensation via Efficient Synthetic-Data Parameterizationcited by 188
  10. 2022Vision GNN: An Image is Worth Graph of Nodescited by 186
  11. 2021A Survey on Neural Speech Synthesiscited by 184
  12. 2022Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Modelscited by 181
  13. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 180
  14. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  15. 2025Multi-agent Architecture Search via Agentic Supernetcited by 179
  16. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 169
  17. 2021Embodied Intelligence via Learning and Evolutioncited by 163
  18. 2022Compute Trends Across Three Eras of Machine Learningcited by 163
  19. 2022On-Device Training Under 256KB Memorycited by 160
  20. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  21. 2021The Low-Rank Simplicity Bias in Deep Networkscited by 154
  22. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 154
  23. 2022Multiview Transformers for Video Recognitioncited by 148
  24. 2023Neural Architecture Search: Insights from 1000 Paperscited by 139
  25. 2021MoViNets: Mobile Video Networks for Efficient Video Recognitioncited by 135
  26. 2022Neural Prompt Searchcited by 135
  27. 2023Prodigy: An Expeditiously Adaptive Parameter-Free Learnercited by 133
  28. 2021CrypTen: Secure Multi-Party Computation Meets Machine Learningcited by 131
  29. 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 131
  30. 2023Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networkscited by 130
  31. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 122
  32. 2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challengescited by 115
  33. 2021LambdaNetworks: Modeling Long-Range Interactions Without Attentioncited by 107
  34. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  35. 2021AutoFlow: Learning a Better Training Set for Optical Flowcited by 102
  36. 2021Involution: Inverting the Inherence of Convolution for Visual Recognitioncited by 99
  37. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 98
  38. 2022Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimizationcited by 97

50 most cited of 1,499 All 1,499 (JSON)