AutoML

Mitarbeiter: Marius Lindauer, Theresa Eimer, Difan Deng
Introduction

To use machine learning (ML), users have to choose between many design options: (i) ML algorithms (ii) pre-processing techniques, (iii) post-processing techniques, (iv) hyperparameter settings, (v) architectures of neural networks and so on. These design decisions are often responsible whether ML systems return random predictions or achieve state-of-the-art performance. Unfortunately, even for ML-experts it is a tedious and error-prone task and thus it is not easy to make these decisions efficiently.

Automated machine learning (AutoML) addresses this challenge by automating the design process such that AutoML tools support users to efficiently develop new ML applications.

Recent Research Topics

Hyperparameter Optimization and Bayesian Optimization

To achieve peak-performance with an algorithm, choosing an appropriate hyperparameter configuration is crucial. Since hyperparameters are often not very intuitive for human developers, it is a tedious and error-prone task to choose these settings. Bayesian Optimization is a sample-efficient approach to find such hyperparameter configurations in an automatic way, saving human developers tremendous amounts of development time.

Neural Architecture Search

Applying deep learning to new datasets also requires to find a well-performing architecture of a deep neural network. Such an architecture influences the performance, but also other metrics, such as inference time, memory consumption etc pp. Unfortunately, it is again not obvious for human developers how to design such deep neural networks making the process fairly inefficient. Neural architecture search is an paradigma to automatically determine the best architectures for new datasets, making new applications of deep learning feasible also at larger scale.

Dynamic Algorithm Configuration

Instead of choosing the hyperparameters of an ML algorithm once, many hyperparameters have to be adapted over time. A well-known example is the learning rate of a deep neural network, which is decreased, sometimes also increased, over time. So far, these dynamic hyperparameters are controlled by a human-designed heuristic, which is often not optimal for a new dataset. Therefore, we develop new approaches for dynamic algorithm configuration, which learns from data how to adjust these on-the-fly.

Interpretability of AutoML 

A major drawback of AutoML tools is the risk that ML will be even a more mysterious black box than it ever was. Therefore, we also develop analysis tools that provide feedback to AutoML users about important insights, such as, (i) how to use AutoML tools more efficiently or (ii) which hyperparameter decisions were important to achieve the final performance. This helps ML developers to get a better understanding of why and how ML and AutoML works.

  • Conference Contributions
    • Andre Biedenkapp, H. Furkan Bozkurt, Theresa Eimer, Frank Hutter, Marius Lindauer
      Algorithm Control: Foundation of a New Meta-Algorithmic Framework
      Proceedings of the European Conference on Artificial Intelligence (ECAI), 2020
    • M. Lindauer and M. Feurer and K. Eggensperger and A. Biedenkapp and F. Hutter
      Towards Assessing the Impact of Bayesian Optimization's Own Hyperparameters
      {IJCAI} 2019 {DSO} Workshop, August 2019
    • M. Feurer and K. Eggensperger and S. Falkner and M. Lindauer and F. Hutter
      Practical Automated Machine Learning for the AutoML Challenge 2018
      ICML 2018 AutoML Workshop, July 2018
  • Book Chapters
    • Hector Mendoza and Aaron Klein and Matthias Feurer and Jost Tobias Springenberg and Matthias Urban and Michael Burkart and Max Dippel and Marius Lindauer and Frank Hutter
      Towards Automatically-Tuned Deep Neural Networks
      AutoML: Methods, Sytems, Challenges, Springer, pp. 141--156, December 2018, edited by Hutter, Frank and Kotthoff, Lars and Vanschoren, Joaquin
  • Technical Report
    • M. Lindauer and K. Eggensperger and M. Feurer and A. Biedenkapp and J. Marben and P. M\"uller and F. Hutter
      BOAH: A Tool Suite for Multi-Fidelity Bayesian Optimization & Analysis of Hyperparameters
      arXiv:1908.06756 [cs.LG], August 2019
    • Marius Lindauer and Frank Hutter
      Best Practices for Scientific Research on Neural Architecture Search
      Arxiv/CoRR, September 2019