Conformal prediction (CP) is a modern machine and statistical learning method that allows to develop valid predictions under weak probabilistic assumptions. CP can be used to form set predictions, using any underlying point predictor, and for very general target variables, allowing the error levels to be controlled by the user. CP has been widely used to develop robust forms of probabilistic prediction methodologies, and applied to many practical real life challenges.

The aim of this symposium is to serve as a forum for the presentation of new and ongoing work and the exchange of ideas between researchers on any aspect of conformal and probabilistic prediction, including their application to interesting problems in any field.

Submission Guidelines

Authors are invited to submit original, English-language research contributions or experience reports. Typical papers should not exceed 20 pages, and formatted according to JMLR (Journal of Machine Learning Research) template and style guidelines. The LaTeX package is available here.

Submission of a paper should be regarded as a commitment that, should the paper be accepted, at least one of the authors will register and attend the symposium to present the work.

Topics

Topics of the symposium include, but are not limited to:

• Theoretical analysis of conformal prediction, including performance guarantees and optimality results.
• Applications of conformal prediction in various fields, including bioinformatics, medicine, large language models and information security.
• Software implementations of conformal and probabilistic prediction frameworks and methods.
• Novel conformity measures.
• Distribution-free uncertainty quantification.
• Conformal anomaly detection.
• Conformal martingale testing and change-point detection.
• Venn prediction and other methods of multi-probability prediction.
• Distributional prediction and conformal predictive distributions.
• Algorithmic theory of randomness.
• Conformal prediction for explainability, causality and fairness, accountability and transparency (FAT).
• Probabilistic prediction.
• On-line compression modelling.

The Committee is open to consider any other recent and cutting edge development related to Conformal and Probabilistic Prediction.

Publication

Submitted papers will be refereed for quality, correctness, originality, and relevance. Notification and reviews will be communicated via email. All accepted papers will be presented at the Symposium and published in the PMLR (Proceedings of Machine Learning Research).

Venue

The conference will be held at Royal Holloway University of London (Egham TW20 0EX, United Kingdom).

Contact

General enquiries: Khuong.Nguyen@rhul.ac.uk