The 39th International Conference on Machine Learning (ICML 2022) will be held in Baltimore, Maryland USA July 17-23, 2022 and is planned to be an in-person conference with virtual elements. In addition to the main conference sessions, the conference will also include Expo, Tutorials, and Workshops. Please submit proposals to the appropriate chairs.

We invite submissions of papers on all topics related to machine learning for the main conference proceedings. All papers will be reviewed in a double-blind process and accepted papers will be presented at the conference. There are three important changes in the reviewing, paper formatting and submission process compared to last year: (i) Reviewing will take place in two phases. (ii) Papers need to be prepared and submitted as a single file: 8 pages as main paper, with unlimited pages for references and appendix. (iii) There will be no separate deadline for the submission of supplementary material. In addition, a new requirement is that upon the acceptance of their papers, at least one of the authors must join the conference, either in person or virtually, or their paper will not be included in the proceedings.

Topics of interest include (but are not limited to):

    General Machine Learning (active learning, clustering, online learning, ranking, reinforcement learning, supervised, semi- and self-supervised learning, time series analysis, etc.)
    Deep Learning (architectures, generative models, deep reinforcement learning, etc.)
    Learning Theory (bandits, game theory, statistical learning theory, etc.)
    Optimization (convex and non-convex optimization, matrix/tensor methods, stochastic, online, non-smooth, composite, etc.)
    Probabilistic Inference (Bayesian methods, graphical models, Monte Carlo methods, etc.)
    Trustworthy Machine Learning (accountability, causality, fairness, privacy, robustness, etc.)
    Applications (computational biology, crowdsourcing, healthcare, neuroscience, social good, climate science, etc.)

Papers published at ICML are indexed in the Proceedings of Machine Learning Research through the Journal of Machine Learning Research.