Ranking & Metrics
Impact Score is a novel metric devised to rank conferences based on the number of contributing the best scientists in addition to the h-index estimated from the scientific papers published by the best scientists. See more details on our methodology page.
Research Impact Score:5.60
Contributing Best Scientists:86
H5-index:
Papers published by Best Scientists156
Research Ranking (Computer Science)71
Conference Call for Papers
The 35th Annual Conference on Learning Theory (COLT 2022) will take place July 2-5, 2022. Assuming the circumstances allow for an in-person conference it will be held in London, UK. 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 in both oral and poster sessions. 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. For eligible papers, authors must indicate at submission time if they wish their paper to be considered for a student paper award. 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
IMPORTANT DATES
(All dates are in 2022.)
Submission deadline: February 9, 4:00 PM PST
Initial Author Response due: April 12
Author Notification: May 14
Conference Dates: July 2-5
Overview
Top Research Topics at Conference on Learning Theory?
Artificial intelligence (20.30%)
Algorithm (19.25%)
Discrete mathematics (18.00%)
The conference investigates studies in Artificial intelligence, Algorithm, Discrete mathematics, Combinatorics and Mathematical optimization.
The research on Artificial intelligence featured in the event combines topics in other fields like Machine learning, Theoretical computer science and Pattern recognition.
The studies on Discrete mathematics discussed can also contribute to research in the domains of Class (set theory), Bounded function, Polynomial and Learnability.
While Combinatorics is the focus of the conference, it also provided insights into the studies of Function (mathematics), Upper and lower bounds and Distribution (mathematics).
While the conference focused on Mathematical optimization, it was also able to explore topics like Regret and Convex optimization.
What are the most cited papers published at the conference?
A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting (14078 citations)
A training algorithm for optimal margin classifiers (8123 citations)
Combining labeled and unlabeled data with co-training (4570 citations)
Research areas of the most cited articles at Conference on Learning Theory:
The most cited publications generally zeroe in on subjects such as Artificial intelligence, Algorithm, Mathematical optimization, Discrete mathematics and Regret.
The works on Artificial intelligence tackled in the most cited publications bring together disciplines like Machine learning, Theoretical computer science and Pattern recognition.
The most cited papers facilitate discussions on Algorithm that incorporate concepts from other fields like Boosting (machine learning) and Perceptron.
What topics the last edition of the conference is best known for?
Artificial intelligence
Statistics
Machine learning
The previous edition focused in particular on these issues:
Conference on Learning Theory aims to foster the development of research in Combinatorics, Applied mathematics, Upper and lower bounds, Regret and Discrete mathematics.
The conference explores issues in Combinatorics which can be linked to other research areas like Distribution (mathematics), Omega and Rank (linear algebra).
The research on Applied mathematics tackled can also make contributions to studies in the areas of Stochastic gradient descent, Convergence (routing), Rate of convergence, Function (mathematics) and Generalization.
Concepts in Gradient descent, as well as related topics in Algorithm, are covered in the Convergence (routing) research presented in the conference.
The study of Regret encompasses disciplines such as Mathematical optimization, as well as fields such as Active learning (machine learning), all of which overlap with one another.
The Discrete mathematics research presented in Conference on Learning Theory explores the relationship between Constant (mathematics) and the closely related topic of Lipschitz continuity.
The most cited articles from the last conference are:
Statistical Query Algorithms and Low Degree Tests Are Almost Equivalent (13 citations)
Corruption-robust exploration in episodic reinforcement learning (6 citations)
Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games (6 citations)
Papers citation over time
A key indicator for each conference is its effectiveness in reaching other researchers with the papers published at that venue.
The chart below presents the interquartile range (first quartile 25%, median 50% and third quartile 75%) of the number of citations of articles over time.
Research.com
Top authors and change over time
The top authors publishing at Conference on Learning Theory (based on the number of publications) are:
Manfred K. Warmuth (47 papers) absent at the last edition,
Peter L. Bartlett (38 papers) published 2 papers at the last edition, 1 more than at the previous edition,
Robert E. Schapire (37 papers) absent at the last edition,
Yishay Mansour (36 papers) published 2 papers at the last edition, 1 more than at the previous edition,
Avrim Blum (32 papers) published 1 paper at the last edition the same number as at the previous edition.
The overall trend for top authors publishing at this conference is outlined below. The chart shows the number of publications at each edition of the conference for top authors.
Research.com
Top affiliations and change over time
Only papers with recognized affiliations are considered
The top affiliations publishing at Conference on Learning Theory (based on the number of publications) are:
Massachusetts Institute of Technology (159 papers) published 15 papers at the last edition, 2 less than at the previous edition,
Microsoft (136 papers) published 10 papers at the last edition, 1 less than at the previous edition,
University of California, Berkeley (105 papers) published 11 papers at the last edition, 4 more than at the previous edition,
Princeton University (99 papers) published 7 papers at the last edition, 3 less than at the previous edition,
Technion – Israel Institute of Technology (92 papers) published 3 papers at the last edition the same number as at the previous edition.
The overall trend for top affiliations publishing at this conference is outlined below. The chart shows the number of publications at each edition of the conference for top affiliations.
Research.com
Publication chance based on affiliation
The publication chance index shows the ratio of articles published by the best research institutions at the conference edition to all articles published within that conference. The best research institutions were selected based on the largest number of articles published during all editions of the conference.
The chart below presents the percentage ratio of articles from top institutions (based on their ranking of total papers).Top affiliations were grouped by their rank into the following tiers: top 1-10, top 11-20, top 21-50, and top 51+. Only articles with a recognized affiliation are considered.
Research.com
During the most recent 2021 edition, 1.37% of publications had an unrecognized affiliation. Out of the publications with recognized affiliations, 50.69% were posted by at least one author from the top 10 institutions publishing at the conference. Another 13.19% included authors affiliated with research institutions from the top 11-20 affiliations. Institutions from the 21-50 range included 20.83% of all publications and 15.28% were from other institutions.
Returning Authors Index
A very common phenomenon observed among researchers publishing scientific articles is the intentional selection of conferences they have already attended in the past. In particular, it is worth analyzing the case when the authors participate in the same conference from year to year.
The Returning Authors Index presented below illustrates the ratio of authors who participated in both a given as well as the previous edition of the conference in relation to all participants in a given year.
Research.com
Returning Institution Index
The graph below shows the Returning Institution Index, illustrating the ratio of institutions that participated in both a given and the previous edition of the conference in relation to all affiliations present in a given year.
Research.com
The experience to innovation index
Our experience to innovation index was created to show a cross-section of the experience level of authors publishing at a conference. The index includes the authors publishing at the last edition of a conference, grouped by total number of publications throughout their academic career (P) and the total number of citations of these publications ever received (C).
The group intervals were selected empirically to best show the diversity of the authors' experiences, their labels were selected as a convenience, not as judgment. The authors were divided into the following groups:
Novice - P < 5 or C < 25 (the number of publications less than 5 or the number of citations less than 25),
Competent - P < 10 or C < 100 (the number of publications less than 10 or the number of citations less than 100),
Experienced - P < 25 or C < 625 (the number of publications less than 25 or the number of citations less than 625),
Master - P < 50 or C < 2500 (the number of publications less than 50 or the number of citations less than 2500),
Star - P ≥ 50 and C ≥ 2500 (both the number of publications greater than 50 and the number of citations greater than 2500).
Research.com
The chart below illustrates experience levels of first authors in cases of publications with multiple authors.
