This is a draft, and will become more curated and more organized as I get more involved with the topic. However, I think the listed resources are definitely worth going through.
- AutoML: Methods, Systems, Challenges (book) (NIPS 2018 Tutorial)
- Taking Human out of Learning Applications: A Survey on Automated Machine Learning (paper) (2019)
- Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search (paper) (2018)
- Efficient and Robust Automated Machine Learning (paper) (NIPS 2015)
- Google Vizier: A Service for Black-Box Optimization (paper) (KDD 2017)
- Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization (paper) (2018)
- Massively Parallel Hyperparameter Tuning (paper) (blog post) (2019)
- Practical Hyperparameter Optimization for Deep Learning (paper) (ICLR 2018)
- Martin Krasser's Guide to Bayesian Methods for Machine Learning (intro blog post) (Tutorials and Notebooks)
- A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning (paper) (2010)
- Taking the Human Out of the Loop: A Review of Bayesian Optimization (paper) (2016)
- Neural Architecture Search with Reinforcement Learning (paper)
- Progressive Neural Architecture Search (paper) (2018)
- Progressive Dynamic Hurdling - The Evolved Transformer (paper) (my slides) (2019)
- Designing Neural Network Architectures using Reinforcement Learning (paper) (2017)
- Genetic CNN (paper) (2017)
- Large-Scale Evolution of Image Classifiers (paper) (2017)
- AmoebaNet: Regularized Evolution for Image Classifier Architecture Search (paper) (2019)
- DARTS: Differentiable Architecture Search (paper) (2018)
- Learning to Learn Using Gradient Descent (paper) (ICANN 2001)
- Learning to Learn without Gradient Descent by Gradient Descent (paper) (ICML 2017)
- A Comparative Analysis of Selection Schemes Used in Genetic Algorithms (paper)