• 自动机器学习 AutoML
• • • Survey (综述文章)：
    • Theory（理论文章）:
    • • Black-box optimization
  • 7.Datasets and Benchmarks
  • 8.AutoML Challenges
  • Applications
  • Other Resources
  • Contributing
  • • Copyright notice

自动机器学习 AutoML

• Papers（论文）
• Introduction and Tutorials (简介与教程)
• AutoML Areas and Papers (研究领域与相关论文)
• Theory and Survey (理论与综述))
• Code (代码)
• Scholars (著名学者)
• Thesis (硕博士论文)
• AutoML Challenges (自动机器学习比赛)
• Applications (应用)
• Other Resources (其他资源)
• Contributing (欢迎参与贡献)
• Copyright notice

---

0.Papers（论文）

Latest papers: (All papers are also put in doc/awesome_papers.md)

Title	Venue	Code	Note
ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies	ArXiv.2021.10		LeiZhang:NOTE
Approximate Neural Architecture Search via Operation Distribution Learning	ArXiv.2021.08		LeiZhang:Note
Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator	CVPR	Github
Speedy Performance Estimation for Neural Architecture Search	NeurIPS	Github	LeiZhang:NOTE
Generic Neural Architecture Search via Regression	NeurIPS	Github	XiangFei:NOTE
Stronger NAS with Weaker Predictors	NeurIPS	Github	LeiZhang:NOTE
Learning Latent Architectural Distribution in Differentiable Neural Architecture Search via Variational Information Maximization	ICCV		LeiZhang:NOTE
Not All Operations Contribute Equally: Hierarchical Operation-adaptive Predictor for Neural Architecture Search	ICCV		XiangFei:NOTE
Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift	ICCV	GitHub	XiangFei:NOTE
RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving	ICCV		LeiZhang:NOTE

---

1.Introduction and Tutorials

Want to quickly learn AutoML？想尽快入门自动机器学习？看下面的教程。

• Books 书籍
• Blogs 博客
• Video tutorials 视频教程
• Brief introduction and slides 简介与ppt资料

---

2.AutoML Areas and Papers

• Survey
• Theory
• Neural Architecture Search
• Hyper Paramater Optimization
• Automatic Network Compression

---

3.Theory and Survey (理论与综述)

Here are some articles on AutoML theory and survey.

Survey (综述文章)：

Title	Venue	Year	Code	Note
Automated Machine Learning	Springer Book	2019	-
Neural architecture search: A survey	JMLR	2019	-
AutonoML: Towards an Integrated Framework for Autonomous Machine Learning	arXiv	2020	-
Taking human out of learning applications: A survey on automated machine learning	arXiv	2018	-
AutoML: A Survey of the State-of-the-Art	arXiv	2019	-
A Survey on Neural Architecture Search	arXiv	2019	-
A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions	ACM Computing Surveys	2021	-
On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice	Neurocomputing	2020	github

Theory（理论文章）:

Black-box optimization

Title	Venue	Code	Note	Year
BORE: Bayesian Optimization by Density-Ratio Estimation	ICML	GitHub	NOTE	2021
Meta Learning Black-Box Population-Based Optimizers	ArXiv	GitHub	NOTE	2021
Transfer Bayesian Optimization	Note/Blog	GitHub	NOTE	2021
HEBO: Heteroscedastic Evolutionary Bayesian Optimisation	NeurIPS 2020 black-box competition	GitHub	NOTE	2020
Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search	NeurIPS	GitHub	NOTE	2020
Scalable Global Optimization via Local Bayesian Optimization	NeuriPS	GitHub	NOTE	2019
Practical Transfer Learning for Bayesian Optimization	ArXiv	-	NOTE	2018
Two-stage transfer surrogate model for automatic hyperparameter optimization	ECML	GitHub	NOTE	2016

---

4.Code (代码)

---

5.Scholars

---

6.Thesis

---

7.Datasets and Benchmarks

---

8.AutoML Challenges

---

Applications

---

Other Resources

---

Contributing

If you are interested in contributing, please refer to HERE for instructions in contribution.

---

Copyright notice

[Notes]This Github repo can be used by following the corresponding licenses. I want to emphasis that it may contain some PDFs or thesis, which were downloaded by me and can only be used for academic purposes. The copyrights of these materials are owned by corresponding publishers or organizations. All this are for better adademic research. If any of the authors or publishers have concerns, please contact me to delete or replace them.