AutoML 2016 - 2016 Workshop on Automatic Machine Learning (AutoML)

Machine learning has been very successful, but its successes rely on human machine learning experts to define the learning problem, select, collect and preprocess the training data, choose appropriate ML architectures (deep learning, random forests, SVMs, …) and their hyperparameters, and finally evaluate the suitability of the learned models for deployment. As the complexity of these tasks is often beyond non-experts, the rapid growth of machine learning applications has created a demand for off-the-shelf machine learning methods that are more bullet-proof and can be used easily without expert knowledge. We call the resulting research area that targets progressive automation of machine learning AutoML.
AutoML aims to automate many different stages of the machine learning process, and encourages contributions in any of the following (or related) areas:
- Model selection, hyper-parameter optimization, and model search
- Meta learning and transfer learning
- Representation learning and automatic feature extraction / construction
- Demonstrations (demos) of working AutoML systems
- Automatic generation of workflows / workflow reuse
- Automatic problem "ingestion" (from raw data and miscellaneous formats)
- Automatic feature transformation to match algorithm requirements
- Automatic detection and handling of skewed data and/or missing values
- Automatic acquisition of new data (active learning, experimental design)
- Automatic report writing (providing insight on automatic data analysis)
- Automatic selection of evaluation metrics / validation procedures
- Automatic selection of algorithms under time/space/power constraints
- Automatic prediction post-processing and calibration
- Automatic leakage detection
- Automatic inference and differentiation
- User interfaces for AutoML
We especially encourage demos of working AutoML systems; demo proposals are submitted through an accompanying paper. We also encourage the participants of the AutoML challenge (http://automl.chalearn.org/) to submit a paper.
The best 2-3 papers will be invited for oral plenary presentation. All other accepted papers will be presented as posters and short poster spotlight presentations. We plan to invite the authors of high-quality submissions to submit extended versions of their work for another round of reviews and publication in the post-workshop proceedings.
For submission details please see http://icml2016.automl.org.
Invited speakers:
- Ryan Adams
- Nando de Freitas (conditional on attending ICML)
- Zoubin Ghahramani (conditional on attending ICML)
- Kevin Leyton-Brown (conditional on attending ICML)
- Kate Smith-Miles
- Alexandre Statnikov: The AutoML Challenge
Chairs: Frank Hutter, Lars Kotthoff, Joaquin Vanschoren
Organizing committee: Pavel Brazdil, Rich Caruana, Christophe Giraud-Carrier, Isabelle Guyon, Balazs Kegl