Automated Machine Learning with Monte-Carlo Tree Search (Extended Version)

@inproceedings{Rakotoarison2019AutomatedML,
  title={Automated Machine Learning with Monte-Carlo Tree Search (Extended Version)},
  author={Herilalaina Rakotoarison and Marc Schoenauer and Mich{\`e}le Sebag},
  booktitle={IJCAI},
  year={2019}
}
The AutoML task consists of selecting the proper algorithm in a machine learning portfolio, and its hyperparameter values, in order to deliver the best performance on the dataset at hand. [...] Key Method Extensive empirical studies are conducted to independently assess and compare: i) the optimization processes based on Bayesian optimization or MCTS; ii) its warm-start initialization; iii) the ensembling of the solutions gathered along the search. Mosaic is assessed on the OpenML 100 benchmark and the Scikit…Expand
TPOT-SH: A Faster Optimization Algorithm to Solve the AutoML Problem on Large Datasets
TLDR
TPOT-SH inspired from the concept of Successive Halving used in Multi-Armed Bandit problems is introduced, which allows TPOT to explore the search space faster and have much better performance on larger datasets.
Naive Automated Machine Learning - A Late Baseline for AutoML
TLDR
Naive AutoML is presented, a very simple solution to AutoML that exploits important meta-knowledge about machine learning problems and makes simplifying, yet, effective assumptions to quickly come to high-quality solutions.
An ADMM Based Framework for AutoML Pipeline Configuration
TLDR
A novel AutoML scheme is proposed by leveraging the alternating direction method of multipliers (ADMM) to decompose the optimization problem into easier sub-problems that have a reduced number of variables and circumvent the challenge of mixed variable categories.
DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filtering
TLDR
This study presents DeepLine, a reinforcement learning-based approach for automatic pipeline generation that utilizes an efficient representation of the search space together with a novel method for operating in environments with large and dynamic action spaces.
Auto-Sklearn 2.0: The Next Generation
TLDR
This paper extends Auto-sklearn with a new, simpler meta-learning technique, improves its way of handling iterative algorithms and enhance it with a successful bandit strategy for budget allocation, and proposes a solution towards truly hand-free AutoML.
Towards Automatic Machine Learning Pipeline Design
TLDR
The results show that the framework can be used both to describe a diverse set of ML programs and to determine unambiguously which AutoML system produced the best ML programs, in many cases, the produced ML programs outperformed ML programs made by human experts.
Surrogate-assisted asynchronous multiobjective algorithm for nuclear power plant operations
TLDR
This work focuses on the optimization of the operation cost and stability of power of a real-life power transient, while maintaining safety standards, and proposes a massive asynchronous parallel master/workers MOEA/D assisted by a surrogate models.
Formal Fields: A Framework to Automate Code Generation Across Domains
TLDR
This work has implemented formal fields as a fully documented open source project applied to the Abstract Reasoning Challenge (ARC), and found code snippets solving twenty two previously unsolved ARC problems.
Automating Data Science: Prospects and Challenges
TLDR
This chapter discusses how to automate important parts of data science, especially in the modeling stages, where techniques such as automated machine learning (AutoML) are gaining traction.
Solving Constrained CASH Problems with ADMM
TLDR
This work presents a recent approach that leverages the ADMM optimization framework to decompose CASH into multiple small problems and demonstrates how ADMM facilitates incorporation of black-box constraints.
...
1
2
...

References

SHOWING 1-10 OF 36 REFERENCES
Efficient and Robust Automated Machine Learning
TLDR
This work introduces a robust new AutoML system based on scikit-learn, which improves on existing AutoML methods by automatically taking into account past performance on similar datasets, and by constructing ensembles from the models evaluated during the optimization.
Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets
TLDR
A generative model for the validation error as a function of training set size is proposed, which learns during the optimization process and allows exploration of preliminary configurations on small subsets, by extrapolating to the full dataset.
Autostacker: a compositional evolutionary learning system
TLDR
An automatic machine learning modeling architecture called Autostacker is introduced that combines an innovative hierarchical stacking architecture and an evolutionary algorithm to perform efficient parameter search without the need for prior domain knowledge about the data or feature preprocessing.
Algorithms for Hyper-Parameter Optimization
TLDR
This work contributes novel techniques for making response surface models P(y|x) in which many elements of hyper-parameter assignment (x) are known to be irrelevant given particular values of other elements.
Monte-Carlo tree search and rapid action value estimation in computer Go
Freeze-Thaw Bayesian Optimization
TLDR
This paper develops a dynamic form of Bayesian optimization for machine learning models with the goal of rapidly finding good hyperparameter settings and provides an information-theoretic framework to automate the decision process.
Sequential Model-Based Optimization for General Algorithm Configuration
TLDR
This paper extends the explicit regression models paradigm for the first time to general algorithm configuration problems, allowing many categorical parameters and optimization for sets of instances, and yields state-of-the-art performance.
Auto-WEKA 2.0: Automatic model selection and hyperparameter optimization in WEKA
TLDR
The new version of Auto-WEKA is described, a system designed to help novice users by automatically searching through the joint space of WEKA's learning algorithms and their respective hyperparameter settings to maximize performance, using a state-of-the-art Bayesian optimization method.
Benchmarking Automatic Machine Learning Frameworks
TLDR
This work tests auto-sklearn, TPOT, auto_ml, and H2O's AutoML solution against a compiled set of regression and classification datasets sourced from OpenML and finds that auto-Sklearn performs the best across classification datasets and TPOT performs thebest across regression datasets.
Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science
TLDR
This paper implements an open source Tree-based Pipeline Optimization Tool (TPOT) in Python and shows that TPOT can design machine learning pipelines that provide a significant improvement over a basic machine learning analysis while requiring little to no input nor prior knowledge from the user.
...
1
2
3
4
...