The conference on Theoretical Foundations of Machine Learning
(TFML 2019) will take place in Kraków, Poland, on February 11-15, 2019.
We invite submissions of papers addressing theoretical aspects of machine learning and related topics. We are interested in theoretically motivated perspectives on these areas:
- algorithms: active learning, representation learning, semi-supervised learning, supervised learning, unsupervised learning
- cheminformatics: activity prediction, drug design
- computational complexity of learning
- deep learning: adversarial networks, attention models, computer vision, generative models, natural language processing, speech recognition
- neuroscience and cognitive science
- optimization methods
- reinforcement learning
Conference is organized by Department of Machine Learning, Institute of Computer Science and Computational Mathematics, Faculty of Mathematics and Computer Science, Jagiellonian University.
The conference will take place at Jagiellonian University, at the Faculty of Mathematics and Computer Science, Cracow, Łojasiewicza 6.
- paper submission -
30 Nov 2018
- decision notification -
5 Jan 2019
- camera ready version -
11 Jan 2019
5-19 Jan 2019
- conference -
11-15 Feb 2019
This year there are two ways of presenting research on the TFML conference:
- original, unpublished research paper, which will be peer reviewed and after acceptance and presentation during the TFML conference published in Schedae Informaticae Journal.
- extended abstract (optionally supplemented with a preprint), which will be also reviewed and after acceptance will result in a presentation during the TFML conference.
All submissions should be prepared in English, according to the Schedae Informaticae template (LaTeX template
). Page limits are as follows:
- research paper - the soft limit (including references, and other additional materials) is 8 pages and a hard limit is 10 pages. Papers longer than 10 pages will be rejected without reviewing. The final paper accepted for the conference should be no longer than 20 pages.
- extended abstract - at most 2 pages.
Papers will be selected via a double-blind peer-review process (the reviewers will not know the identities of the authors, and vice versa). It will be up to the authors to ensure the proper anonymization of their paper. In particular, the first page cannot include names or affiliations of the authors. When referring to one's own work, use the third person, rather than the first person. Violation of the above rules may lead to rejection without review.