COLT 2025 : Conference on Learning Theory
Call For Paper (CFP) Description
The 38th Annual Conference on Learning Theory (COLT 2025) will take place June 30th-July 4th, 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.
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.
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 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 COLT.
PAPER 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. The program committee may decline to make these awards, or may split them among several papers.
DUAL SUBMISSIONS POLICY
Conferences: In general, 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 may not be submitted to COLT.
Journals: In general, submissions that are substantially similar to papers that have been previously published, accepted for publication, or submitted in parallel to journals may not be submitted to COLT.
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 have been made. Authors will have an opportunity to address the issues brought up in the reviews.
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; as such, the interaction between authors and referees is meant to both figure this out and guide the paper into a publishable state.
We recommend the following video for a thoughtful discussion of such aims and related issues: IACR Distinguished Lecture: Caught in Between Theory and Practice
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.
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 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 COLT.
PAPER 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. The program committee may decline to make these awards, or may split them among several papers.
DUAL SUBMISSIONS POLICY
Conferences: In general, 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 may not be submitted to COLT.
Journals: In general, submissions that are substantially similar to papers that have been previously published, accepted for publication, or submitted in parallel to journals may not be submitted to COLT.
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 have been made. Authors will have an opportunity to address the issues brought up in the reviews.
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; as such, the interaction between authors and referees is meant to both figure this out and guide the paper into a publishable state.
We recommend the following video for a thoughtful discussion of such aims and related issues: IACR Distinguished Lecture: Caught in Between Theory and Practice
Conference Topics
Frequently Asked Questions
What is COLT 2025 : Conference on Learning Theory?
COLT 2025 : Conference on Learning Theory is Join the 38th Annual Conference on Learning Theory (COLT 2025) from June 30th to July 4th, 2025, in Lyon, France, to discuss the theoretical aspects of machine learning and its intersection with computer science, statistics, and applied mathematics.
How do I submit my paper to COLT 2025 : Conference on Learning Theory?
Submit your paper via the official submission portal at https://learningtheory.org/colt2025. Follow the submission guidelines outlined in the CFP.
How do I register for the COLT 2025 : Conference on Learning Theory?
Register at https://learningtheory.org/colt2025. Early registration is recommended to secure your spot and avail discounts.
What are the important dates for COLT 2025 : Conference on Learning Theory?
- Start Date: 30 Jun, 2025
- End Date: 04 Jul, 2025
- End Date: 04 Jul, 2025
What is the location and date of COLT 2025 : Conference on Learning Theory?
COLT 2025 : Conference on Learning Theory will be held on 30 Jun, 2025 - 04 Jul, 2025 at Lyon, France. More details about the event location and travel arrangements can be found on the conference’s official website.
What is the location of COLT 2025 : Conference on Learning Theory?
COLT 2025 : Conference on Learning Theory will be held at Lyon, France.
Can I submit more than one paper to COLT 2025 : Conference on Learning Theory?
Yes, multiple submissions are allowed, provided they align with the conference’s themes and topics. Each submission will be reviewed independently.
What is the review process for submissions?
Papers will be reviewed by a panel of experts in the field, ensuring that only high-quality, relevant work is selected for presentation. Each paper will be evaluated on originality, significance, and clarity.
What presentation formats are available at COLT 2025 : Conference on Learning Theory?
Presentations can be made in various formats including oral presentations, poster sessions, or virtual presentations. Specific details will be provided upon acceptance of your paper.
Can I make changes to my submission after I’ve submitted it?
Modifications to your submission are allowed until the submission deadline. After that, no changes can be made. Please make sure all details are correct before submitting.
What are the benefits of attending COLT 2025 : Conference on Learning Theory?
Attending COLT 2025 : Conference on Learning Theory provides an opportunity to present your research, network with peers and experts in your field, and gain feedback on your work. Additionally, it is an excellent platform for career advancement and collaboration opportunities.
What should I include in my abstract or proposal submission?
Your abstract or proposal should include a concise summary of your paper, including its purpose, methodology, and key findings. Ensure that it aligns with the conference themes.