Call for papers
Submissions
We encourage submissions of extended abstracts with a varied set of topics:
the intersection of any area of machine learning and continuous-time methods (this includes optimisation, neural architectures, generative models);
the incorporation of knowledge of continuous systems to analyse and improve on discrete approaches;
the exploration of approaches from dynamical systems and related fields to machine learning;
the software tools from the numerical analysis community which can be used for ML;
applications of continuous-time based ML methods to new problem domains.
We encourage exploratory submissions which suggest novel ideas of how to better incorporate continuous time systems in machine learning.
Submitted papers can be up to four pages long, not including references, plus unlimited space for references. The use of 10-point Times font is mandatory. Any paper exceeding this length will be automatically rejected.
We do not allow papers which have been already accepted at another venue.
Submission deadline
The submission deadline with be June 1st 2022, 23:59 Pacific Time.
Submission instructions
Papers can be submitted through CMT here: https://cmt3.research.microsoft.com/CTMML2022/
Submissions do not need to be anonymised.
Submissions should use the 1-column ICML format. Submissions need to be at most 4 pages, with unlimited pages for references. No supplementary materials can be submitted.
To obtain a one column format in ICML, please use the command obtained from the ICML style files here.
\onecolumn
Timeline for accepted papers
The camera ready deadline is 7th of July 2022.
All papers should upload a video to SlidesLive by 3rd of July 2022. Videos should be 3 minutes in length; videos for contributed talks should be 10 minutes in length.
The poster session at ICML will be in person. For authors attending in person, please have a poster of A1 portrait format. If no author is attending in person, there is the option to print a poster or to upload a soft poster for the website.