Neural Architecture Search Using Deep Neural Networks and Monte Carlo Tree Search
Open accessAbstract
Neural Architecture Search (NAS) has shown great success in automating the design of neural networks, but the prohibitive amount of computations behind current NAS methods requires further investigations in improving the sample efficiency and the network evaluation cost to get better results in a shorter time. In this paper, we present a novel scalable Monte Carlo Tree Search (MCTS) based NAS agent, named AlphaX, to tackle these two aspects. AlphaX improves the search efficiency by adaptively balancing the exploration and exploitation at the state level, and by a Meta-Deep Neural Network (DNN) to predict network accuracies for biasing the search toward a promising region. To amortize the network evaluation cost, AlphaX accelerates MCTS rollouts with a distributed design and reduces the number of epochs in evaluating a network by transfer learning, which is guided with the tree structure in MCTS. In 12 GPU days and 1000 samples, AlphaX found an architecture that reaches 97.84% top-1 accuracy on CIFAR-10, and 75.5% top-1 accuracy on ImageNet, exceeding SOTA NAS methods in both the accuracy and sampling efficiency. Particularly, we also evaluate AlphaX on NASBench-101, a large scale NAS dataset; AlphaX is 3x and 2.8x more sample efficient than Random Search and Regularized Evolution in finding the global optimum. Finally, we show the searched architecture improves a variety of vision applications from Neural Style Transfer, to Image Captioning and Object Detection.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
MCTS balances exploration and exploitation to effectively navigate large decision spaces.
“The Monte Carlo Tree Search (MCTS) algorithm is a strategic search method that balances exploration and exploitation to effectively navigate large decision spaces [25, 34].”
From Optimizing Neural Network Architecture for Medical Image Segmentation Using Monte Carlo Tree Search (2026) · cites this paper as [25]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625 · see citing works
Greff, K., Srivastava, R. K., Koutnik, J., Steunebrink, B. R., & Schmidhuber, J. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2582924 · Cited by 6,955 · see citing works
Flagged first, then by citations
Research works printed but not linked: 22
- Auer, P.; Cesa-Bianchi, N.; and Fischer, P. 2002. Finite- time analysis of the multiarmed bandit problem. Machine learning 47(2-3):235-256.
- Bergstra, J. S.; Bardenet, R.; Bengio, Y.; and Kégl, B. 2011. Algorithms for hyper-parameter optimization. In Advances in neural information processing systems, 2546-2554.
- Chen, Y.; Meng, G.; Zhang, Q.; Xiang, S.; Huang, C.; Mu, L.; and Wang, X. 2019. Renas: Reinforced evolutionary neural architecture search. In Proceedings of the IEEE Con- ference on Computer Vision and Pattern Recognition, 4787- 4796.
- Elsken, T.; Metzen, J.-H.; and Hutter, F. 2017. Simple and efficient architecture search for convolutional neural net- works. arXiv preprint arXiv:1711.04528. · arXiv
- Kandasamy, K.; Schneider, J.; and Póczos, B. 2015. High dimensional bayesian optimisation and bandits via additive models. In International Conference on Machine Learning, 295-304.
- Kocsis, L., and Szepesvári, C. 2006. Bandit based monte- carlo planning. In European conference on machine learn- ing, 282-293. Springer.
- Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.; Fu, C.-Y.; and Berg, A. C. 2016. Ssd: Single shot multibox detector. In European conference on computer vision, 21- 37. Springer.
- Liu, C.; Zoph, B.; Shlens, J.; Hua, W.; Li, L.-J.; Fei- Fei, L.; Yuille, A.; Huang, J.; and Murphy, K. 2017a. Progressive neural architecture search. arXiv preprint arXiv:1712.00559. · arXiv
- Liu, C.; Zoph, B.; Shlens, J.; Hua, W.; Li, L.-J.; Fei-Fei, L.; Yuille, A.; Huang, J.; and Murphy, K. 2017b. Progressive Neural Architecture Search. Liu, H.; Simonyan, K.; Vinyals, O.; Fernando, C.; and Kavukcuoglu, K. 2017c. Hierarchical representa- tions for efficient architecture search. arXiv preprint arXiv:1711.00436. · arXiv
- Liu, H.; Simonyan, K.; Simonyan, K.; and Yang, Y. 2018. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055. · arXiv
- Luo, R.; Tian, F.; Qin, T.; Chen, E.; and Liu, T.-Y. 2018. Neural architecture optimization. In Bengio, S.; Wallach, H.; Larochelle, H.; Grauman, K.; Cesa-Bianchi, N.; and Gar- nett, R., eds., Advances in Neural Information Processing Systems 31.
- Nachum, O.; Norouzi, M.; and Schuurmans, D. 2016. Im- proving policy gradient by exploring under-appreciated re- wards. arXiv preprint arXiv:1611.09321. · arXiv
- Negrinho, R., and Gordon, G. 2017. Deeparchitect: Auto- matically designing and training deep architectures. arXiv preprint arXiv:1704.08792. · arXiv
- Pham, H.; Guan, M. Y.; Zoph, B.; Le, Q. V.; and Dean, J. 2018. Efficient neural architecture search via parameter sharing. arXiv preprint arXiv:1802.03268. · arXiv
- Real, E.; Aggarwal, A.; Huang, Y.; and Le, Q. V. 2018. Reg- ularized evolution for image classifier architecture search. arXiv preprint arXiv:1802.01548. · arXiv
- Sciuto, C.; Yu, K.; Jaggi, M.; Musat, C.; and Salzmann, M. 2019. Evaluating the search phase of neural architecture search. arXiv preprint arXiv:1902.08142. · arXiv
- Silver, D.; Huang, A.; Maddison, C. J.; Guez, A.; Sifre, L.; Van Den Driessche, G.; Schrittwieser, J.; Antonoglou, I.; Panneershelvam, V.; Lanctot, M.; et al. 2016. Mastering the game of go with deep neural networks and tree search. nature 529(7587):484-489.
- Tian, Y.; Ma, J.; Gong, Q.; Sengupta, S.; Chen, Z.; Pinker- ton, J.; and Zitnick, C. L. 2019. ELF opengo: An analysis and open reimplementation of alphazero. CoRR abs/1902.04522. · arXiv
- Wistuba, M. 2017. Finding competitive network ar- chitectures within a day using uct. arXiv preprint arXiv:1712.07420. · arXiv
- Xu, K.; Ba, J.; Kiros, R.; Cho, K.; Courville, A.; Salakhudi- nov, R.; Zemel, R.; and Bengio, Y. 2015. Show, attend and tell: Neural image caption generation with visual at- tention. In International conference on machine learning, 2048-2057.
- Ying, C.; Klein, A.; Real, E.; Christiansen, E.; Murphy, K.; and Hutter, F. 2019. Nas-bench-101: Towards re- producible neural architecture search. arXiv preprint arXiv:1902.09635. · arXiv
- Zoph, B.; Vasudevan, V.; Shlens, J.; and Le, Q. V. 2017. Learning transferable architectures for scalable im- age recognition. arXiv preprint arXiv:1707.07012. · arXiv
Cited by
Sorted by citations
Optimizing Neural Network Architecture for Medical Image Segmentation Using Monte Carlo Tree Search
Meng, L., Nie, F., Zhang, Y., & Han, C. (2026) · arXiv · doi:10.48550/arxiv.2602.22361
“In this approach, MCTS evaluates the most promising actions at each state, while the MNAS-Unet architecture learns the performance characteristics of sampled architectures and generalizes this knowledge to unexplored architectural configurations [25].”
- Authors
- Wang, L., Zhao, Y., Jinnai, Y., Tian, Y., & Fonseca, R.
- Affiliations
- Brown University (US)
- Worcester Polytechnic Institute (US)
- Meta (United States) (US)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2020-04-03
- Volume
- 34
- Issue
- 06
- Pages
- 9983-9991
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2997699039
- Cited by
- 124
- References
- 2
- Citations by year
- 2026: 1 · 2025: 16 · 2024: 16 · 2023: 22 · 2022: 16 · 2021: 29 · 2020: 18 · 2019: 6
- FWCI
- 6.46
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- www.aaai.org/ (unspecified)
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Physical Sciences › Computer Science › Artificial Intelligence › Evolutionary Algorithms and Applications
- Keywords
- neural architecture search, Monte Carlo tree search, sample efficiency, accuracy prediction, transfer learning, exploration-exploitation balance, visual task, image captioning, object detection, neural style transfer
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
