The goal of this workshop is to strengthen the network of people interested in machine learning (ML) theory in Denmark, in particular to foster collaborations, to provide a forum for PhD students, and to bridge the gap between theory and practice. The workshop invites a variety of contributions:

• Short talks (5-10 minutes) and/or posters
• Longer tutorial and overview talks (20-40 minutes)

You are welcome to present your latest research (ongoing or just published) and to give tutorial and overview talks reviewing existing work. We invite presentations of open problems, both open theoretical problems and “theory for practice presentations”, where challenges in applied AI are presented that may profit from ML theory.

Submission guidelines

Submit an abstract (at most 3000 characters) for your contribution.

Deadline for submission: 15-07-2025

Notification of acceptance: 01-08-2025

Note: If your abstract gets accepted, one of the co-authors must present in person and register for the Danish Digitalization, Data Science and AI 3.0 conference.

List of topics

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 deep learning
• Theoretical explanation of empirical phenomena in learning
• Supervised learning
• Unsupervised, semi-supervised learning, self-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
• Real-world problems that could profit from ML theory

Organizing committee

• Nirupam Gupta (nigu@di.ku.dk), UCPH
• Christian Igel (igel@di.ku.dk), UCPH
• Pola Schwöbel, Amazon
• Ole Winther, UCPH, DTU