The Algorithmic Learning Theory (ALT) 2021 conference will be held in Paris, France on March 16–19, 2021. The conference is dedicated to all theoretical and algorithmic aspects of machine learning. We invite submissions with contributions to new or existing learning problems including, but not limited to:

    Design and analysis of learning algorithms.
    Statistical and computational learning theory.
    Online learning algorithms and theory.
    Optimization methods for learning.
    Unsupervised, semi-supervised and active learning.
    Interactive learning, planning and control, and reinforcement learning.
    Privacy-preserving data analysis.
    Learning with additional societal considerations: e.g., fairness, economics.
    Robustness of learning algorithms to adversarial agents.
    Artificial neural networks, including deep learning.
    High-dimensional and non-parametric statistics.
    Adaptive data analysis and selective inference.
    Learning with algebraic or combinatorial structure.
    Bayesian methods in learning.
    Learning in distributed and streaming settings.
    Game theory and learning.
    Learning from complex data: e.g., networks, time series.
    Theoretical analysis of probabilistic graphical models.

While the primary focus of the conference is theoretical, authors are welcome to support their analysis by including relevant experimental results.

Accepted papers will be published electronically in the Proceedings of Machine Learning Research (PMLR), and will be presented at the conference as a full-length talk.  Authors of accepted papers will have the option of opting out of the proceedings in favor of a 1-page extended abstract, which will point to an open access archival version of the full paper reviewed for ALT. At least one author of each accepted paper should be present at the conference to present the work.