CAp 2023 Call for Papers

03/07/2023 – 05/07/2023 all-day

Date : 2023-07-03 => 2023-07-05
Lieu : Strasbourg

CAp is an interdisciplinary gathering of researchers at the intersection of machine learning, applied mathematics, and related areas. This year it takes place at Strasbourg from July 3 to July 5 and is part of the platform PFIA (3-7 July) gathering researchers in Artificial Intelligence.

The submission website can be found here.
Submitted papers can be either in English or in French and we encourage two types of submissions:

  • Full research papers on the theme of machine learning theory and its applications should not exceed 10 pages in CAp double-column format (including references and figures). A suitable LaTeX template for CAp is available here.
  • Short papers can be up to 6 pages using the same format as the full papers. They present original ideas and provide an opportunity to describe significant work in progress.

We also encourage the submission of recent (2022 or 2023) papers accepted to high level conferences and journals in machine learning. These papers will also be reviewed (lightly) by the program committee. If accepted, they will be presented at the conference but will not appear in any (online) proceedings. Note that, in this particular case, the paper can be submitted in the original conference format (length and style) and the reviews given by the conference/ML journal where it was accepted should be included as the first pages of the submission in addition to a link to the corresponding conference/ML journal web page. The submission of the reviews and the original paper should be merged and submitted into a single PDF file on the easychair website.

Some accepted papers will be presented in a long (20 minutes) oral presentation and all the accepted papers will be given the opportunity to be presented as a spotlight (3 minutes) and as a poster at the conference. These presentations are an opportunity to have constructive and rigorous feedbacks, as well as to establish contacts with members of the french machine learning community. PhD Students are particularly welcome and encouraged to submit papers. Contributions will be freely distributed on the conference website, subject to approval by the authors.


  • CAp Event: 3-5 July 2022
  • PFIA Event: 3-7 July 2022
  • CAp papers submission deadline: 1st of March 2023
  • Notification to authors for CAp papers: 15th of April 2023
  • Camera ready: 2nd of May 2023
  • Opening for registration: 22nd of April 2023
  • Early bird registration for the conference: up to the 23rd of May 2023


The conference and program chairs of CAp 2023 invite those working in areas related to any aspect of machine learning to submit original papers for review. Solicited topics include, but are not limited to:

Learning theory, models and paradigms:

  • Active learning
  • Online learning
  • Multi-target, multi-task, multi-instance, multi-view and transfer learning
  • Supervised, unsupervised and semi-supervised learning
  • Reinforcement learning
  • Relational learning
  • Representation learning
  • Symbolic learning
  • Bandit algorithms
  • Matrix and tensor factorization
  • Optimal Transport for Machine Learning
  • Ethic and fairness of Machine Learning
  • Interpretable Machine Learning
  • Grammar induction
  • Kernel methods
  • Bayesian methods
  • Spectral methods
  • Stochastic processes
  • Ensemble learning and boosting
  • Graphical models
  • Gaussian process
  • Neural networks and deep learning
  • Learning theory
  • Game theory

Optimization et related problems:

  • Large-scale machine learning and optimization
  • Optimization algorithms
  • Distributed optimization
  • Machine learning and structured data (spatio-temporal data, tree, graph)
  • Classification with missing values


  • Social network analysis
  • Temporal data analysis
  • Bioinformatic
  • Data mining
  • Neuroscience
  • Natural language processing
  • Information retrieval
  • Computer vision

Lien direct

Notre site web :
Suivez-nous sur Tweeter : @GDR_MADICS
Pour vous désabonner de la liste, suivre ce lien.