Neural Architecture Search & AutoML

Architecture search, hyperparameter optimization, automated ML.

A topic in the Science corpus, drawn from 198 papers.

Trusted voices in Neural Architecture Search & AutoML

Ordered by the trust Neural Architecture Search & AutoML's own network concentrates on each researcher, most first.

  1. Frank Hutter — trusted by 368 researchers here
  2. Risto Miikkulainen — trusted by 250 researchers here
  3. Kenneth O. Stanley — trusted by 224 researchers here
  4. Katharina Eggensperger — trusted by 89 researchers here
  5. Holger H. Hoos — trusted by 112 researchers here
  6. Kevin Leyton-Brown — trusted by 110 researchers here
  7. Aaron Klein — trusted by 113 researchers here
  8. Lingxi Xie — trusted by 121 researchers here
  9. Hiroaki Kitano — trusted by 58 researchers here
  10. Daniel L. K. Yamins — trusted by 99 researchers here
  11. Alan L. Yuille — trusted by 103 researchers here
  12. James Bergstra — trusted by 99 researchers here

Most-cited papers in Neural Architecture Search & AutoML

Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.

  1. Optuna: A Next-generation Hyperparameter Optimization Framework (2019) — 10,668 citations
  2. Taking the Human Out of the Loop: A Review of Bayesian Optimization (2016) — 5,660 citations
  3. Evolving Neural Networks through Augmenting Topologies (2002) — 3,694 citations
  4. Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures (2013) — 2,576 citations
  5. AutoML: A Survey of the State-of-the-Art (2019, Knowledge-Based Systems) — 1,830 citations
  6. Auto-WEKA: combined selection and hyperparameter optimization of classification algorithms (2012) — 1,705 citations
  7. Designing Neural Network Architectures using Reinforcement Learning (2016) — 1,553 citations
  8. BOHB: Robust and Efficient Hyperparameter Optimization at Scale (2018) — 1,347 citations
  9. Hyperparameter Optimization (2017) — 1,336 citations
  10. Tune: A Research Platform for Distributed Model Selection and Training (2018) — 1,129 citations
  11. ParamILS: An Automatic Algorithm Configuration Framework (2014) — 1,129 citations
  12. Single Path One-Shot Neural Architecture Search with Uniform Sampling (2019) — 1,036 citations
  13. SNAS: Stochastic Neural Architecture Search (2018, International Conference on Learning Representations) — 1,014 citations
  14. Evolving Deep Neural Networks (2017) — 962 citations
  15. Genetic CNN (2017) — 931 citations
  16. Auto-Keras: An Efficient Neural Architecture Search System (2018) — 924 citations
  17. NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search (2020) — 863 citations
  18. Understanding and Simplifying One-Shot Architecture Search (2018) — 824 citations
  19. NAS-Bench-101: Towards Reproducible Neural Architecture Search (2019) — 821 citations
  20. Hyperopt: A Python Library for Optimizing the Hyperparameters of Machine Learning Algorithms (2013) — 808 citations
  21. SMASH: One-Shot Model Architecture Search through HyperNetworks (2017) — 808 citations
  22. Random Search and Reproducibility for Neural Architecture Search (2019) — 807 citations
  23. Progressive Differentiable Architecture Search: Bridging the Depth Gap Between Search and Evaluation (2019) — 738 citations
  24. Searching for a Robust Neural Architecture in Four GPU Hours (2019) — 719 citations
  25. TPOT: A Tree-based Pipeline Optimization Tool for Automating Machine Learning (2016) — 712 citations
  26. PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search (2019) — 703 citations
  27. Hyper-Parameter Optimization: A Review of Algorithms and Applications (2020) — 690 citations
  28. Designing neural networks through neuroevolution (2019) — 683 citations
  29. Neural Architecture Search with Bayesian Optimisation and Optimal Transport (2018) — 666 citations
  30. Auto-WEKA 2.0: Automatic model selection and hyperparameter optimization in WEKA (2017) — 652 citations
  31. Speeding Up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves (2015) — 642 citations
  32. Efficient Architecture Search by Network Transformation (2017) — 633 citations
  33. A genetic programming approach to designing convolutional neural network architectures (2017) — 618 citations
  34. Analyzing Inverse Problems with Invertible Neural Networks (2018) — 598 citations
  35. An Efficient Approach for Assessing Hyperparameter Importance (2014) — 550 citations
  36. Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution (2018) — 546 citations
  37. Practical Block-Wise Neural Network Architecture Generation (2017) — 531 citations
  38. A System for Massively Parallel Hyperparameter Tuning (2018) — 521 citations
  39. Bayesian Optimization with Robust Bayesian Neural Networks (2016) — 510 citations
  40. Cormorant: Covariant Molecular Neural Networks (2019) — 498 citations
  41. Deep feature synthesis: Towards automating data science endeavors (2015) — 486 citations
  42. Forward and Reverse Gradient-Based Hyperparameter Optimization (2017) — 477 citations
  43. Benchmark and Survey of Automated Machine Learning Frameworks (2019) — 449 citations
  44. NAS-Unet: Neural Architecture Search for Medical Image Segmentation (2019) — 434 citations
  45. A self-organising network that grows when required (2002) — 418 citations
  46. Understanding and Robustifying Differentiable Architecture Search (2019) — 415 citations
  47. BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search (2019) — 413 citations
  48. Accelerating Neural Architecture Search using Performance Prediction (2017) — 390 citations
  49. Collaborative hyperparameter tuning (2013) — 384 citations
  50. Evaluating the Search Phase of Neural Architecture Search (2019) — 375 citations

Most active researchers

By papers in this topic: a volume measure, not trust.