Call for papers

Call for Papers

The ICLR 2020 Workshop on Neural Architecture Search (NAS 2020)

Collocated with ICLR 2020, April 26, 2020

Web: https://sites.google.com/view/nas2020

----------------------------------------------------------------

Important Dates:

Submission deadline: 7 February 2020, 11:59pm UTC-12 (Feb 7 anywhere in the world; extended until the day after the ICML deadline by popular request)

Notification: 25 February 2020

----------------------------------------------------------------

Neural Architecture Search (NAS) is the logical next step in automating the learning of representations. It follows upon the recent transition from manual feature engineering to automatically learning features (using a fixed neural architecture) by replacing manual architecture engineering with automated architecture design. NAS can be seen as a subfield of automated machine learning (AutoML) and has significant overlap with hyperparameter optimization and meta-learning. NAS methods have already outperformed manually-designed architectures on several tasks, such as image classification, object detection or semantic segmentation. They have also already found architectures that yield a better trade-off between resource consumption on target hardware and predictive performance.

The goal of this workshop is to bring together researchers from industry and academia that focus on NAS in order to build a strong, open, inclusive and welcoming community behind it. We invite submissions on the following topics:

  • Gradient-based NAS
  • Weight-sharing methods
  • Bayesian optimization
  • Evolutionary algorithms
  • Reinforcement learning
  • Hyperparameter optimization
  • Meta-learning and transfer learning
  • Predictive models of performance
  • Multi-fidelity optimization methods
  • Benchmarking and robustness of NAS
  • Applications of NAS to various tasks

Since NAS often relies on high computational demands and substantial engineering efforts, a particular focus of this workshop is on reproducibility. We therefore encourage authors to open-source their code and results and will take this into account in the decision making process. As part of the submission, authors will have to indicate which parts of the NAS best practices checklist they satisfy.

Submissions should be up to 4 pages in ICLR format (plus references and an appendix of up to 10 pages). All accepted papers will be presented as posters. We may invite the best 2-3 papers for an oral plenary presentation. Unless indicated by the authors, we will provide PDFs of all accepted papers on the workshop website. There will be no archival proceedings. For submission details please see the submission page.

Keynote Speakers

Location

As the main ICLR 2020 conference, the 1st NAS workshop will be fully virtual and will take place on April 26th. Details on how exactly this will work will be provided soon.

Tentative Dates

  • January 27th: Submission system opens
  • February 7th (anywhere on earth): Submission deadline
  • February 21st: Reviewing deadline
  • February 25th: Author notification
  • April 2nd April 4th (anywhere on Earth): Camera Ready Copy due
  • April 26th: Workshop day