TNT logo Zur zentralen Website der Leibniz Universität Hannover Bannerlogo des Instituts für Informationsveratbeitung

RONAS: Runtime-Optimized NAS

Im Rahmen des Projekts AutoML


To achieve top performance, applying deep learning to new tasks often requires new architectures of deep neural networks. However, finding such architectures is often a tedious and error-prone task for human developers. The field of neural architecture search (NAS) addresses this challenge by studying different ways of automatically finding optimal architectures. So far, neural architecture search (NAS) was mostly applied to achieve good performance in terms of accuracy (or similar generalization metrics). A current research direction is not only to achieve great accuracy, but also to achieve it fast---in some applications, you cannot afford to wait hours or days to train your neural network. To this end, a recent competition, called DAWNbench, measured time-to-accuracy, i.e., how fast can a neural network achieve a pre-defined accuracy (e.g., 94% on CIFAR-10). In this project, we will study how we can build a NAS system that performs well wrt time-to-accuracy by applying techniques from algorithm configuration.


We strongly recommend that students should have hands-on experience for the following topics:

To apply for this project, please send us an email with the following information:
  1. Which ML-related courses have you taken?
  2. Can you please attach your transcript of records?
  3. Which projects have you done so far (in Hannover and elsewhere)?
  4. Which topics interest you most?

  5. Since different projects require different skill sets, please also rate your skills in the following categories on a scale from ++ (very good) to -- (no knowledge/skill):
  6. Creativity / ideas for developing new algorithms
  7. Getting someone else's large code base to run
  8. Running comprehensive experimental studies / keeping track of results
  9. Self-motivation to push through even if things don't work for a while
  10. Coding skills
    1. Python
    2. TensorFlow
    3. Keras
    4. PyTorch
    5. C/C++
  11. Ability to read a RL paper, implement it and get it to work
  12. Ability to read a DL paper, implement it and get it to work
  13. Ansprechpartner: Marius Lindauer