Call for Papers: COLT 2025

The 38th Annual Conference on Learning Theory (COLT 2025) will take place from June 30 to July 4, 2025, in Lyon, France. We invite submissions of papers addressing theoretical aspects of machine learning, broadly defined as a subject at the intersection of computer science, statistics, and applied mathematics. We strongly support an inclusive view of learning theory, including fundamental theoretical aspects of learnability in various contexts, and theory that sheds light on empirical phenomena.

Topics of Interest

The topics include but are not limited to:

• Design and analysis of learning algorithms
• Statistical and computational complexity of learning
• Optimization methods for learning, including online and stochastic optimization
• Theory of artificial neural networks, including deep learning
• Theoretical explanation of empirical phenomena in learning
• Supervised learning
• Unsupervised, semi-supervised learning, domain adaptation
• Learning geometric and topological structures in data, manifold learning
• Active and interactive learning
• Reinforcement learning
• Online learning and decision-making
• Interactions of learning theory with other mathematical fields
• High-dimensional and non-parametric statistics
• Kernel methods
• Causality
• Theoretical analysis of probabilistic graphical models
• Bayesian methods in learning
• Game theory and learning
• Learning with system constraints (e.g., privacy, fairness, memory, communication)
• Learning from complex data (e.g., networks, time series)
• Learning in neuroscience, social science, economics and other subjects

Submissions by authors who are new to COLT are encouraged. While the primary focus of the conference is theoretical, authors are welcome to support their analysis with relevant experimental results.

Submission Guidelines

• Formatting: Submissions are limited to 12 PMLR formatted pages, excluding references. An additional supplementary file may be uploaded that can include unlimited appendices. All details, proofs, and derivations required to substantiate the results must be included in the submission, possibly in the appendices. However, the contribution, novelty, and significance of submissions will be judged primarily based on the main paper (without appendices).
• Anonymization: Submissions should be suitable for double-blind reviewing. They should NOT include author names or other identifying information. Refer to your own prior work in the third person and do not include acknowledgments in the submission.
• Style files: Please use the provided LaTeX style files and template. The "[anon]" option in the LaTeX template should be used to suppress author names. You can download them from: LaTeX style files and template
• Submission Portal: Papers should be submitted through CMT: https://cmt3.research.microsoft.com/COLT2025

Important Dates

All dates are in 2025:

• Submission deadline: February 6, 5:00 PM EST
• Reviews released: March 28
• Initial author response due: April 4
• Discussion period: April 4–11
• Author notification: May 2
• Conference dates: June 30–July 4

Reviewing Philosophy

We strongly encourage constructive feedback that can help authors improve their work. The aim of the reviewing process is to assess whether the work is close to being ready for publication, and the interaction between authors and referees is meant to guide the paper into a publishable state.

Rebuttal Phase

As in previous years, there will be a rebuttal phase during the review process. Initial reviews will be sent to authors before final decisions are made, and authors will have an opportunity to address the issues brought up in the reviews.

Awards

COLT will award both best paper and best student paper awards. To be eligible for the best student paper award, the primary contributor(s) must be full-time students at the time of submission.

Dual Submissions Policy

Submissions that are substantially similar to papers that have been previously published, accepted for publication, or submitted in parallel to other peer-reviewed conferences with proceedings or journals may not be submitted to COLT.

Publication

Accepted papers will be presented at the conference. At least one author of each accepted paper should present the work at the conference. Accepted papers will be published electronically in the Proceedings of Machine Learning Research (PMLR). Authors 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.

Call for Open Problems

COLT 2025 will feature a session devoted to the presentation of open problems. A description of these problems will also appear in the COLT proceedings.

• Submission Deadline: June 6, AoE
• Content: A clearly defined problem, motivation, current state, and relevant references.
• Length: At most 4 pages long, excluding references.
• Format: COLT 2025 format. The title should start with "Open Problem:".
• Anonymity: Submissions are non-anonymous; they should contain authors’ names.
• Submission Site: CMT Website for Open Problems track: https://cmt3.research.microsoft.com/COLT2025/Submission/Index
• Contact: Vianney Perchet (Open Problems Chair) at vianney.perchet@gmail.com.

Contact Information

• Program Chairs: colt2025programchairs@gmail.com
• Sponsorships: sponsorships@learningtheory.org